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

    Neuronpedia

    INDEX
    Explanations

    Go

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soph
    -0.08
    практи
    -0.07
    equip
    -0.07
    راتيج
    -0.07
    考核
    -0.07
    Flash
    -0.06
    곶
    -0.06
    网页
    -0.06
    Units
    -0.06
     glyphicon
    -0.06
    POSITIVE LOGITS
     hijos
    0.07
    ("""
    0.07
    (codec
    0.07
     Following
    0.07
    [text
    0.07
    จา
    0.06
    .Scope
    0.06
    因为我们
    0.06
    integral
    0.06
    ѿ
    0.06
    Act Density 0.008%

    No Known Activations