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

    Neuronpedia

    INDEX
    Explanations

    applied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    227
    -0.07
     字
    -0.06
     هذا
    -0.06
    Rec
    -0.06
    ampus
    -0.06
    �
    -0.06
     предназнач
    -0.06
     reputation
    -0.06
    启
    -0.06
     Auxiliary
    -0.06
    POSITIVE LOGITS
    (man
    0.07
    ілля
    0.06
    -required
    0.06
     encourages
    0.06
    (ALOAD
    0.06
    edback
    0.06
    ImageData
    0.06
    inte
    0.06
    //--------------------------------------------------------------------------------
    0.06
    uminum
    0.06
    Act Density 0.023%

    No Known Activations