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

    Neuronpedia

    INDEX
    Explanations

    -----

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Bus
    -0.08
    üssen
    -0.08
    ASF
    -0.08
    _fc
    -0.07
    FFE
    -0.07
    FirstChild
    -0.07
    >About
    -0.07
    buster
    -0.07
     personnel
    -0.07
    .Logging
    -0.07
    POSITIVE LOGITS
    -----
    0.09
    -----↵
    0.09
     lenght
    0.07
     dü
    0.07
    棣
    0.07
    dü
    0.07
     -----
    0.07
     הרי
    0.07
     рай
    0.06
    狀況
    0.06
    Act Density 0.003%

    No Known Activations