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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocos
    -0.06
     Location
    -0.06
    kur
    -0.06
    스티
    -0.06
    ピー
    -0.06
    ת
    -0.06
     ¬
    -0.06
     Electoral
    -0.06
     kino
    -0.06
     поб
    -0.06
    POSITIVE LOGITS
     '''
↵
    0.07
    召
    0.06
     phường
    0.06
    .Inventory
    0.06
     budget
    0.06
    ++){↵
    0.06
    <Token
    0.06
    (abs
    0.06
    Submission
    0.06
    (FLAGS
    0.06
    Act Density 0.000%

    No Known Activations