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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ummer
    -0.63
    openConnection
    -0.63
     loop
    -0.57
     droop
    -0.55
    Slf
    -0.54
    DoubleQuotes
    -0.54
    plink
    -0.52
    ple
    -0.52
    ples
    -0.51
    unkel
    -0.49
    POSITIVE LOGITS
     محفوظة
    0.71
    ed
    0.71
    et
    0.64
    ing
    0.62
     Савезне
    0.60
    ers
    0.59
    ets
    0.57
    ette
    0.57
    minster
    0.57
    ettes
    0.56
    Act Density 0.426%

    No Known Activations