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

    Neuronpedia

    INDEX
    Explanations

    collapse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ์โ
    -0.06
    Its
    -0.06
    ิร
    -0.06
    OVER
    -0.06
    mouseover
    -0.06
    χής
    -0.06
     REAL
    -0.06
    Enterprise
    -0.06
    _And
    -0.06
    /hooks
    -0.06
    POSITIVE LOGITS
     expulsion
    0.07
     obsessive
    0.07
     toxicity
    0.07
    ANCED
    0.07
     Crunch
    0.06
     Expanded
    0.06
     عل
    0.06
     $\
    0.06
     geldi
    0.06
     polishing
    0.06
    Act Density 0.001%

    No Known Activations