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

    Neuronpedia

    INDEX
    Explanations

    Hockey lines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LOW
    -0.07
     pw
    -0.07
     ohio
    -0.07
     blowjob
    -0.06
    velop
    -0.06
    242
    -0.06
     fluorescent
    -0.06
     cough
    -0.06
     Convenient
    -0.06
     вули
    -0.06
    POSITIVE LOGITS
     TestData
    0.06
     $($
    0.06
    ниці
    0.06
    []=$
    0.06
     awakeFromNib
    0.06
    -authored
    0.06
     gilt
    0.06
    .readlines
    0.06
    /ex
    0.06
    .Component
    0.06
    Act Density 0.015%

    No Known Activations