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
    .ov
    -0.09
    inzwe
    -0.08
    ifty
    -0.07
    -cover
    -0.07
    addle
    -0.07
    issed
    -0.07
     gratuitement
    -0.07
    itung
    -0.07
    ાયક
    -0.07
    pas
    -0.07
    POSITIVE LOGITS
     developments
    0.14
     ontwikkelingen
    0.12
     newer
    0.12
     increasingly
    0.11
    新时代
    0.11
     emerging
    0.11
    的发展
    0.11
    未来
    0.10
     технологий
    0.10
     시대
    0.10
    Act Density 0.031%

    No Known Activations