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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CTL
    -0.06
    rokes
    -0.06
    -slot
    -0.06
    “One
    -0.06
     muscular
    -0.06
    finite
    -0.06
    -fluid
    -0.06
     KIND
    -0.06
    _SPR
    -0.06
     муж
    -0.06
    POSITIVE LOGITS
     Ivy
    0.07
     Woods
    0.07
     wik
    0.06
     celebration
    0.06
     doby
    0.06
     postfix
    0.06
     chap
    0.06
     QPointF
    0.06
     maté
    0.06
    ()->
    0.06
    Act Density 0.073%

    No Known Activations