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

    Neuronpedia

    INDEX
    Explanations

    Code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inert
    -0.07
    olum
    -0.06
     Frozen
    -0.06
    一卷
    -0.06
     добре
    -0.06
     khá
    -0.06
    dummy
    -0.06
     Coleman
    -0.06
    उ
    -0.06
     Follow
    -0.06
    POSITIVE LOGITS
    /map
    0.07
    .Photo
    0.07
    uč
    0.07
    .det
    0.07
     جد
    0.06
    iso
    0.06
     Error
    0.06
     sun
    0.06
    ่าการ
    0.06
    loggedin
    0.06
    Act Density 0.000%

    No Known Activations