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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ساز
    -0.06
     Farrell
    -0.06
    \Notifications
    -0.06
    ыш
    -0.06
    	that
    -0.06
     яс
    -0.06
     competing
    -0.06
    ﾉ
    -0.06
     especial
    -0.06
    ireccion
    -0.06
    POSITIVE LOGITS
     Draws
    0.07
    ltk
    0.07
     Graves
    0.07
    ügen
    0.07
    LEAR
    0.06
     Guide
    0.06
     Milk
    0.06
    .exp
    0.06
    IND
    0.06
    -seven
    0.06
    Act Density 0.001%

    No Known Activations