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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SCII
    -0.07
    eting
    -0.07
     להגיד
    -0.07
    agree
    -0.06
     classy
    -0.06
    CEEDED
    -0.06
    .credit
    -0.06
    mega
    -0.06
    etry
    -0.06
     samo
    -0.06
    POSITIVE LOGITS
     Nightmare
    0.07
     fictional
    0.07
    ру
    0.07
     Abbott
    0.07
    ?'
    0.07
    頻道
    0.06
    Rh
    0.06
     الأول
    0.06
    ℎ
    0.06
    ının
    0.06
    Act Density 0.076%

    No Known Activations