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

    Neuronpedia

    INDEX
    Explanations

    izing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tennis
    -0.07
    plans
    -0.07
     تب
    -0.07
    札
    -0.06
     fantastic
    -0.06
    收录
    -0.06
     readFile
    -0.06
     compulsory
    -0.06
     drastic
    -0.06
    .Basic
    -0.06
    POSITIVE LOGITS
     characterization
    0.11
     characterize
    0.10
     characterized
    0.09
    186
    0.07
    ’
    0.07
    character
    0.07
    ifying
    0.07
    urations
    0.07
     lon
    0.07
    aptors
    0.07
    Act Density 0.007%

    No Known Activations