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

    Neuronpedia

    INDEX
    Explanations

    Code and configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eyond
    -0.08
    .SizeMode
    -0.07
    ademic
    -0.07
    .LocalDateTime
    -0.06
    asher
    -0.06
    iliary
    -0.06
    (lo
    -0.06
     Postal
    -0.06
     beyond
    -0.06
    EY
    -0.06
    POSITIVE LOGITS
    こう
    0.07
    (case
    0.07
    гу
    0.07
    rstrip
    0.07
    qrstuvwxyz
    0.07
    ++++++++
    0.06
     дити
    0.06
     rè
    0.06
     WAIT
    0.06
    rava
    0.06
    Act Density 0.056%

    No Known Activations