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

    Neuronpedia

    INDEX
    Explanations

    unstructured text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Provides
    -0.07
     Tb
    -0.07
    ЙЙ
    -0.07
     Nan
    -0.06
     Tablet
    -0.06
     RU
    -0.06
    .store
    -0.06
     خشک
    -0.06
     Colum
    -0.06
     extract
    -0.06
    POSITIVE LOGITS
    ॉय
    0.07
    iter
    0.07
    هدف
    0.07
    aptor
    0.07
    ++];↵
    0.06
    lead
    0.06
     hypo
    0.06
    δα
    0.06
    Mutation
    0.06
    ulations
    0.06
    Act Density 0.000%

    No Known Activations