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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     이용
    -0.08
    osas
    -0.07
    _SHARE
    -0.06
    لية
    -0.06
    Unavailable
    -0.06
    sville
    -0.06
     unset
    -0.06
     Healing
    -0.06
     Crisis
    -0.06
    mercial
    -0.06
    POSITIVE LOGITS
    (expect
    0.06
    ारन
    0.06
    Compiler
    0.06
     corr
    0.06
     Kash
    0.06
     spir
    0.06
     Annotation
    0.06
     Dresden
    0.06
    /min
    0.06
    ández
    0.06
    Act Density 0.024%

    No Known Activations