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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusivity or comprehensiveness

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

    all, every, whole

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protoimpl
    -0.51
    MLLoader
    -0.50
    protoimpl
    -0.48
     Monastery
    -0.46
    cepan
    -0.46
     parch
    -0.45
    none
    -0.44
    sidemargin
    -0.44
    大地
    -0.43
    ardless
    -0.43
    POSITIVE LOGITS
     transfieras
    0.41
     Exactos
    0.39
    transQ
    0.37
    StoryboardSegue
    0.36
     CanadaChoose
    0.36
     saveiro
    0.36
    amssymb
    0.35
    //
    0.35
    Weblinks
    0.35
    BASELINE
    0.34
    Act Density 0.099%

    No Known Activations