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

    Neuronpedia

    INDEX
    Explanations

    biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifestyle
    -0.07
    ?!↵↵
    -0.06
    ycler
    -0.06
    ”.↵↵
    -0.06
    -delete
    -0.06
    ствует
    -0.06
    .links
    -0.06
     writable
    -0.06
     весь
    -0.06
    power
    -0.06
    POSITIVE LOGITS
     guardian
    0.07
    _MODE
    0.07
    OutOfRange
    0.07
     Sponsor
    0.07
    iw
    0.07
     Internal
    0.06
     anale
    0.06
    ُع
    0.06
     appl
    0.06
     معماری
    0.06
    Act Density 0.044%

    No Known Activations