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

    Neuronpedia

    INDEX
    Explanations

    PM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PM
    -1.33
    PM
    -1.10
     pm
    -0.70
    PMG
    -0.63
     Pm
    -0.63
     AssemblyCulture
    -0.61
    Πηγές
    -0.60
     FM
    -0.57
    ormány
    -0.57
     חיצוניים
    -0.56
    POSITIVE LOGITS
    er
    0.75
    ar
    0.66
    s
    0.66
    erl
    0.59
    en
    0.57
     ExecuteAsync
    0.56
    cipation
    0.56
    us
    0.54
    y
    0.54
    nast
    0.53
    Act Density 0.178%

    No Known Activations