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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uces
    -0.06
     çıkart
    -0.06
    حت
    -0.06
    าล
    -0.06
    -stats
    -0.06
    uce
    -0.06
    _REGION
    -0.06
     olsun
    -0.06
    =pk
    -0.06
    ..:
    -0.05
    POSITIVE LOGITS
    trace
    0.07
     fragment
    0.07
    ");↵↵
    0.07
    Br
    0.07
     banning
    0.07
    "));↵↵
    0.07
    Crow
    0.06
    คร
    0.06
    ))↵
    0.06
     приступ
    0.06
    Act Density 0.012%

    No Known Activations