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

    Neuronpedia

    INDEX
    Explanations

    learn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     licenses
    -0.07
    	setTimeout
    -0.07
    away
    -0.07
     prediction
    -0.06
     descriptions
    -0.06
     Theater
    -0.06
     gee
    -0.06
    etry
    -0.06
     UserData
    -0.06
    kt
    -0.06
    POSITIVE LOGITS
    νη
    0.06
     одні
    0.06
    _he
    0.06
    _Detail
    0.06
    ická
    0.06
    oğun
    0.06
     że
    0.06
     uninsured
    0.06
     Spicer
    0.06
    -compose
    0.05
    Act Density 0.024%

    No Known Activations