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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ds
    -0.08
    Serial
    -0.06
    Kevin
    -0.06
    _MIX
    -0.06
     jquery
    -0.06
     corr
    -0.06
    .cgi
    -0.06
     htons
    -0.06
     Yang
    -0.06
     Dragons
    -0.06
    POSITIVE LOGITS
     Have
    0.07
     istiyorum
    0.07
    _external
    0.06
    tach
    0.06
    ศจ
    0.06
    盛
    0.06
    ्बन
    0.06
     kanal
    0.06
    atel
    0.06
    輯
    0.06
    Act Density 0.014%

    No Known Activations