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

    Neuronpedia

    INDEX
    Explanations

    importing python libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pounds
    1.89
    holomorphic
    1.83
     Zijn
    1.83
    ^{+}\
    1.81
    য়ে
    1.81
     juba
    1.80
    !--
    1.79
     bounded
    1.79
     fija
    1.78
     реб
    1.72
    POSITIVE LOGITS
    いますが
    2.10
     graphene
    2.03
    enaar
    2.01
    ഡ്
    1.90
    𝐚
    1.88
     perspectivas
    1.87
    ται
    1.84
    𝐡
    1.82
    helial
    1.80
    𝐢
    1.80
    Act Density 0.000%

    No Known Activations