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

    Neuronpedia

    INDEX
    Explanations

    Biographical information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .contrib
    -0.07
     rede
    -0.07
     Mode
    -0.07
    asset
    -0.07
     (('
    -0.07
     Countdown
    -0.07
    .ad
    -0.06
     UDP
    -0.06
     obscene
    -0.06
    .vars
    -0.06
    POSITIVE LOGITS
    etto
    0.06
     bloody
    0.06
    ?”
    0.06
    	go
    0.06
     slo
    0.06
    敢
    0.06
    /#{
    0.06
     Hubb
    0.06
     अवध
    0.06
    )*/↵
    0.06
    Act Density 0.012%

    No Known Activations