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
    _equal
    -0.07
    urence
    -0.07
     пись
    -0.06
     léka
    -0.06
     Ок
    -0.06
    /project
    -0.06
     firebase
    -0.06
     SHOULD
    -0.06
     Bishop
    -0.06
    	bar
    -0.06
    POSITIVE LOGITS
    asics
    0.07
    ."));↵
    0.06
     finanční
    0.06
     сез
    0.06
     ин
    0.06
    禁
    0.06
     immersed
    0.06
     miraculous
    0.06
     plush
    0.06
    มน
    0.06
    Act Density 0.069%

    No Known Activations