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

    Neuronpedia

    INDEX
    Explanations

    modest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARIO
    -0.08
     annotate
    -0.08
    onian
    -0.07
    “A
    -0.07
    rewrite
    -0.07
    ategories
    -0.07
     contagious
    -0.07
     TAX
    -0.07
     Ethiopian
    -0.07
    ATER
    -0.07
    POSITIVE LOGITS
     modest
    0.08
    �
    0.07
    .statusStrip
    0.07
     ספר
    0.07
    千方百
    0.07
    .AbsoluteConstraints
    0.07
     McKin
    0.07
    מדינ
    0.06
    翕
    0.06
    澽
    0.06
    Act Density 0.003%

    No Known Activations