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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <double
    -0.07
    789
    -0.07
    TIM
    -0.06
     Moderator
    -0.06
    [new
    -0.06
    лась
    -0.06
     newSize
    -0.06
    _timeout
    -0.06
    tile
    -0.06
    .retry
    -0.06
    POSITIVE LOGITS
     lens
    0.07
     compliance
    0.07
     Tolkien
    0.06
     Washing
    0.06
     phục
    0.06
     CrossRef
    0.06
     chặt
    0.06
    ای
    0.06
    еним
    0.06
    	sn
    0.06
    Act Density 0.051%

    No Known Activations