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

    Neuronpedia

    INDEX
    Explanations

    Spanish words such as "ya" and accented characters or words used in programming contexts

    oai_token-act-pair · gemini-2.0-flash

    yes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     كومونز
    -0.89
    rungsseite
    -0.77
     &___
    -0.74
    SourceChecksum
    -0.70
    таратура
    -0.69
     pleaſure
    -0.65
    مراجع
    -0.60
     متعلقه
    -0.58
     ujednoznacz
    -0.58
    httphttps
    -0.57
    POSITIVE LOGITS
     already
    1.54
    Already
    1.49
     Already
    1.47
    already
    1.44
     ALREADY
    1.34
    ALREADY
    1.23
     allerede
    0.96
     уже
    0.93
    既に
    0.93
    すでに
    0.91
    Act Density 0.906%

    No Known Activations