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

    Neuronpedia

    INDEX
    Explanations

    URL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trapped
    -0.07
     primera
    -0.07
    Sounds
    -0.06
    Guild
    -0.06
     Lace
    -0.06
    这
    -0.06
     만들어
    -0.06
     Surrey
    -0.06
    元
    -0.06
    Electric
    -0.06
    POSITIVE LOGITS
    ообраз
    0.08
     presentViewController
    0.07
    تبر
    0.06
     prezident
    0.06
    ilit
    0.06
    ційної
    0.06
     vois
    0.06
     premiere
    0.06
    '])->
    0.06
     Dere
    0.06
    Act Density 0.004%

    No Known Activations