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

    Neuronpedia

    INDEX
    Explanations

    math/science/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ̈
    -0.07
     통해
    -0.07
     Depend
    -0.06
    _locals
    -0.06
     bgcolor
    -0.06
     credible
    -0.06
     standart
    -0.06
    136
    -0.06
    693
    -0.06
     corpor
    -0.06
    POSITIVE LOGITS
     emotionally
    0.06
    (TEST
    0.06
    (/[
    0.06
     ARGS
    0.06
    Templates
    0.06
    corner
    0.06
    .ge
    0.06
    [^
    0.06
     музы
    0.06
    ValueHandling
    0.06
    Act Density 0.035%

    No Known Activations