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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yük
    -0.07
    �
    -0.07
    incl
    -0.07
     �
    -0.06
     hö
    -0.06
     ViewState
    -0.06
     Beef
    -0.06
    ouses
    -0.06
    �
    -0.06
    larıyla
    -0.06
    POSITIVE LOGITS
     출
    0.06
     закон
    0.06
     사건
    0.06
     instructed
    0.06
     eternity
    0.06
    월까지
    0.06
     treated
    0.06
     быть
    0.06
     société
    0.06
     solved
    0.06
    Act Density 0.000%

    No Known Activations