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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social roles and relationships

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

    snowball

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AdapterFactory
    -0.59
    isContained
    -0.55
     Thick
    -0.53
    ChildScrollView
    -0.51
    PYX
    -0.50
    tagext
    -0.49
    ukone
    -0.49
    AutoScaleMode
    -0.48
    msgTypes
    -0.48
    protoimpl
    -0.47
    POSITIVE LOGITS
    ंदीखरीदारी
    0.35
     esboço
    0.32
    endpush
    0.32
     تكبرها
    0.32
     față
    0.31
    évaluateur
    0.31
     betre
    0.30
    ówczas
    0.30
     prieš
    0.29
     domínio
    0.29
    Act Density 0.029%

    No Known Activations