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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    或者
    -0.06
    ABS
    -0.06
    .access
    -0.06
    imal
    -0.06
    -century
    -0.06
    ีบ
    -0.06
    ArrayOf
    -0.05
    ему
    -0.05
     bathrooms
    -0.05
    ifty
    -0.05
    POSITIVE LOGITS
     تغ
    0.07
     Gren
    0.07
     Raptors
    0.07
     меш
    0.07
    swagen
    0.07
     留
    0.07
     trú
    0.07
    toBeTruthy
    0.06
    bilt
    0.06
    undai
    0.06
    Act Density 0.015%

    No Known Activations