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

    Neuronpedia

    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	to
    -0.07
    Crit
    -0.07
     ley
    -0.06
    *T
    -0.06
     Charm
    -0.06
    cat
    -0.06
    订单
    -0.06
     interpreter
    -0.06
     quad
    -0.06
    -Token
    -0.06
    POSITIVE LOGITS
     textu
    0.07
    ,key
    0.06
     osobních
    0.06
     Measurement
    0.06
     besar
    0.06
    ersh
    0.06
     Kenya
    0.06
    (bitmap
    0.06
     responders
    0.06
    ，小
    0.06
    Act Density 0.043%

    No Known Activations