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

    Neuronpedia

    INDEX
    Explanations

    unsafe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    งข
    -0.07
    >({↵
    -0.07
     thử
    -0.07
    ambio
    -0.06
    _MEDIA
    -0.06
    Descri
    -0.06
     ориг
    -0.06
     arz
    -0.06
     pz
    -0.06
    _vid
    -0.06
    POSITIVE LOGITS
     Phrase
    0.06
     displaced
    0.06
    shine
    0.06
    ÇÃO
    0.06
    َج
    0.06
    ція
    0.06
     Ramsey
    0.06
    セン
    0.06
     compute
    0.06
    lead
    0.06
    Act Density 0.002%

    No Known Activations