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

    Neuronpedia

    INDEX
    Explanations

    (x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dear
    -0.07
    tep
    -0.07
    モデル
    -0.07
     techniques
    -0.06
    із
    -0.06
     TSA
    -0.06
     welded
    -0.06
     Nietzsche
    -0.06
    dsa
    -0.06
    Heavy
    -0.06
    POSITIVE LOGITS
    .scrollHeight
    0.07
     inserts
    0.06
    .keyCode
    0.06
    ROT
    0.06
    INV
    0.06
     Cly
    0.06
     органи
    0.06
    相手
    0.06
     consisting
    0.06
     inflated
    0.06
    Act Density 0.006%

    No Known Activations