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
     li
    -0.06
    ideal
    -0.06
     inf
    -0.06
    olor
    -0.06
    (Parse
    -0.06
     Rapid
    -0.06
     array
    -0.06
    лася
    -0.06
    信用
    -0.06
    itched
    -0.06
    POSITIVE LOGITS
     înt
    0.07
     Gret
    0.07
     спир
    0.06
    _PART
    0.06
    (PC
    0.06
     geliştir
    0.06
     �
    0.06
     THPT
    0.06
    ्रश
    0.06
    イル
    0.06
    Act Density 0.065%

    No Known Activations