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

    Neuronpedia

    INDEX
    Explanations

    language expressing friendliness and comfort

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

    associated with positive experiences

    np_acts-logits-general · gemini-2.0-flash

    comfort, politeness, relaxation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.67
    SharedDtor
    -0.65
    endpush
    -0.64
    IBarButtonItem
    -0.63
    GEBURTS
    -0.61
    TemporalType
    -0.60
    ModelAdmin
    -0.59
     getApp
    -0.58
    getKeyCode
    -0.58
    SerializedSize
    -0.58
    POSITIVE LOGITS
    بوابة
    0.74
     surroundings
    0.71
     confines
    0.70
     enough
    0.69
     atmosphere
    0.69
     knowing
    0.67
     yet
    0.61
     environs
    0.58
     conditions
    0.58
    addContainerGap
    0.58
    Act Density 0.135%

    No Known Activations