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

    Neuronpedia

    INDEX
    Explanations

    codes and citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     logged
    -0.07
    -editor
    -0.07
    yg
    -0.07
     Mohammed
    -0.06
    ovic
    -0.06
    ″N
    -0.06
     Moody
    -0.06
    bv
    -0.06
     token
    -0.06
    xo
    -0.06
    POSITIVE LOGITS
    0.08
    "https
    0.06
     تحت
    0.06
    0.06
    0.06
    }*
    0.06
     मतलब
    0.06
    ={{
    0.06
     tbsp
    0.06
    。そして
    0.06
    Act Density 0.257%

    No Known Activations