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

    Neuronpedia

    INDEX
    Explanations

    noun suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ACIONES
    0.39
    AVA
    0.34
    ÇÕES
    0.32
     covert
    0.31
     ethical
    0.31
     intros
    0.31
     relatively
    0.31
    IDADES
    0.31
     chatt
    0.31
     exc
    0.31
    POSITIVE LOGITS
    ulation
    0.44
    arithmic
    0.43
    ination
    0.43
    xiety
    0.42
    itude
    0.42
    itory
    0.41
    ification
    0.41
    ography
    0.41
    inology
    0.41
    ition
    0.40
    Act Density 2.127%

    No Known Activations