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

    Neuronpedia

    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    belongsTo
    -0.07
    стру
    -0.07
     sé
    -0.07
    Normalization
    -0.06
     rendre
    -0.06
    (serializers
    -0.06
     Sé
    -0.06
     HEADER
    -0.06
    inta
    -0.06
    enzhen
    -0.06
    POSITIVE LOGITS
     Blast
    0.07
    .CompareTo
    0.07
    第二
    0.07
    .statistics
    0.06
     omez
    0.06
     beyaz
    0.06
     Vegan
    0.06
    Smoke
    0.06
    .rb
    0.06
     UserId
    0.06
    Act Density 0.092%

    No Known Activations