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

    Neuronpedia

    INDEX
    Explanations

    next

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rouw
    -0.06
    ()}}↵
    -0.06
    활
    -0.06
    :].
    -0.06
    Tabla
    -0.06
     أجل
    -0.06
    }());↵
    -0.06
    bing
    -0.06
     الرح
    -0.06
    виг
    -0.06
    POSITIVE LOGITS
     form
    0.07
     ratified
    0.07
    _prod
    0.07
    だった
    0.07
     sus
    0.07
     selbst
    0.07
     guest
    0.06
     ups
    0.06
     Mich
    0.06
    (piece
    0.06
    Act Density 0.013%

    No Known Activations