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

    Neuronpedia

    INDEX
    Explanations

    Programming/web development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cts
    -0.07
     perfect
    -0.07
    观
    -0.07
     Christina
    -0.07
    ském
    -0.07
     vision
    -0.07
     tohoto
    -0.06
     firefox
    -0.06
    XC
    -0.06
     yaygın
    -0.06
    POSITIVE LOGITS
    .Perform
    0.07
     demean
    0.07
    Due
    0.07
     dreadful
    0.06
    BlockSize
    0.06
     getMax
    0.06
    >\↵
    0.06
    .HOUR
    0.06
    _ALERT
    0.06
    _Handler
    0.06
    Act Density 0.015%

    No Known Activations