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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <N
    -0.07
    ippers
    -0.07
    geo
    -0.07
    äß
    -0.07
     Persistence
    -0.07
    ifter
    -0.06
     安
    -0.06
    /C
    -0.06
    Entr
    -0.06
    ΗΣ
    -0.06
    POSITIVE LOGITS
    %',↵
    0.07
     pl
    0.06
    	button
    0.06
    ")↵
    0.06
    ruc
    0.06
     invol
    0.06
     birkaç
    0.06
    ]).↵
    0.06
     separate
    0.06
    .textLabel
    0.06
    Act Density 0.138%

    No Known Activations