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

    Neuronpedia

    INDEX
    Explanations

    pytorch code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _atomic
    -0.06
    urr
    -0.06
    arda
    -0.06
    esidir
    -0.06
     모르
    -0.06
    urm
    -0.06
    lara
    -0.06
     tend
    -0.06
     Nietzsche
    -0.06
    _bh
    -0.06
    POSITIVE LOGITS
    συ
    0.07
     glob
    0.06
    _EXEC
    0.06
    .setHorizontalGroup
    0.06
     uży
    0.06
     XMLHttpRequest
    0.06
    MAN
    0.06
    arbeit
    0.06
     QUI
    0.06
     adalah
    0.06
    Act Density 0.014%

    No Known Activations