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

    Neuronpedia

    INDEX
    Explanations

    calculator code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     individually
    -0.08
     porque
    -0.08
     warm
    -0.08
     funcional
    -0.08
     breakdown
    -0.08
     thoroughly
    -0.07
     Drupal
    -0.07
    (Cache
    -0.07
     pero
    -0.07
    Clan
    -0.07
    POSITIVE LOGITS
     Replace
    0.09
    Replace
    0.08
    INPUT
    0.08
    .replace
    0.08
    बस
    0.08
    rstrip
    0.08
     Sanit
    0.08
    _join
    0.08
     Allowed
    0.08
     拼
    0.08
    Act Density 0.002%

    No Known Activations