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

    Neuronpedia

    INDEX
    Explanations

    sl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oa
    -0.08
    QUARE
    -0.07
     人
    -0.06
    žít
    -0.06
    ンディ
    -0.06
    _ROUT
    -0.06
    $con
    -0.06
    _bad
    -0.06
     adjacent
    -0.06
    -U
    -0.06
    POSITIVE LOGITS
    htmlspecialchars
    0.07
    _MEDIA
    0.07
    lier
    0.06
     sost
    0.06
     ket
    0.06
     specializing
    0.06
    Mi
    0.06
     innocence
    0.06
    _CONTROLLER
    0.06
     wd
    0.06
    Act Density 0.001%

    No Known Activations