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

    Neuronpedia

    INDEX
    Explanations

    company initiatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     초
    -0.06
    _predicate
    -0.06
     diag
    -0.06
     Friedman
    -0.06
    ecimal
    -0.06
    igram
    -0.06
     sucking
    -0.06
     neredeyse
    -0.06
     beberapa
    -0.06
    POSITIVE LOGITS
     PCR
    0.07
    长
    0.06
    ladığ
    0.06
     коміс
    0.06
    лина
    0.06
     hiçbir
    0.06
    مار
    0.06
    송
    0.06
    964
    0.06
     realistically
    0.06
    Act Density 0.022%

    No Known Activations