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

    Neuronpedia

    INDEX
    Explanations

    female

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IPO
    -0.06
     merged
    -0.06
     Lanka
    -0.06
     fø
    -0.06
     wine
    -0.06
     god
    -0.06
     بق
    -0.06
    ="";↵
    -0.06
    pizza
    -0.06
    -image
    -0.06
    POSITIVE LOGITS
    탈
    0.07
    ẳng
    0.07
    像是
    0.07
    _Row
    0.07
    0.06
    VOID
    0.06
    ylül
    0.06
    Welcome
    0.06
    ามารถ
    0.06
    แรก
    0.06
    Act Density 0.002%

    No Known Activations