Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to grammatical number, particularly focusing on singular and plural forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Plurality or multiplicity

    np_acts-logits-general · gemini-2.0-flash

    many, plural, and singular relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    новништво
    -0.45
     lèvres
    -0.40
    harapkan
    -0.38
    RegistryLite
    -0.35
     désolés
    -0.35
     cafetería
    -0.35
    Diweddarwch
    -0.33
    AnimationsModule
    -0.33
     voran
    -0.33
    ásica
    -0.32
    POSITIVE LOGITS
    ManyToOne
    0.87
    OneToMany
    0.85
    hasMany
    0.77
    WithMany
    0.77
    ToMany
    0.69
    OneToOne
    0.67
    ManyToMany
    0.66
    oneofs
    0.65
    HasOne
    0.65
     Plural
    0.63
    Act Density 0.585%

    No Known Activations