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

    Neuronpedia

    INDEX
    Explanations

    below

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prachtige
    -0.09
    玩的
    -0.08
     Ine
    -0.08
    방
    -0.08
     pretending
    -0.08
     vandaag
    -0.08
     beginners
    -0.08
    �
    -0.08
    િક્ષ
    -0.07
     прекрас
    -0.07
    POSITIVE LOGITS
     threshold
    0.09
    criterion
    0.08
    Criterion
    0.08
     criterion
    0.08
     warranted
    0.08
     stig
    0.08
     criteria
    0.07
     cuotas
    0.07
     predetermined
    0.07
     predefined
    0.07
    Act Density 0.054%

    No Known Activations