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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _require
    -0.06
    DataTable
    -0.06
    _HEALTH
    -0.06
    _match
    -0.06
    ology
    -0.06
    .").
    -0.06
     itibar
    -0.06
    _pixels
    -0.06
     Officer
    -0.06
    <Int
    -0.06
    POSITIVE LOGITS
    orea
    0.07
     нашей
    0.06
    Slash
    0.06
    ."↵↵↵
    0.06
     replacements
    0.06
     furnace
    0.06
     fluct
    0.06
     diesen
    0.06
    ę
    0.06
     baja
    0.06
    Act Density 0.041%

    No Known Activations