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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (include
    -0.07
     seaside
    -0.06
     finely
    -0.06
    .addTab
    -0.06
     volunte
    -0.06
    ディア
    -0.06
    帮助
    -0.06
    .hits
    -0.06
    13
    -0.06
    .barDockControl
    -0.06
    POSITIVE LOGITS
     controversial
    0.07
     sex
    0.07
     Alternate
    0.07
     JB
    0.06
     المو
    0.06
     noi
    0.06
    \Customer
    0.06
    lady
    0.06
    ocab
    0.06
    ΑΓ
    0.06
    Act Density 0.066%

    No Known Activations