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

    Neuronpedia

    INDEX
    Explanations

    documentation or tutorials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tricks
    -0.07
     above
    -0.07
    てしまって
    -0.07
    adan
    -0.07
    mad
    -0.06
     .↵↵↵↵
    -0.06
    利物浦
    -0.06
    Prem
    -0.06
    دس
    -0.06
    Hp
    -0.06
    POSITIVE LOGITS
    _draft
    0.08
    studio
    0.07
    -gay
    0.07
    (bg
    0.07
    .tensor
    0.07
     çalışmaları
    0.07
     GLOBAL
    0.07
    нос
    0.07
    .reference
    0.07
    发起
    0.07
    Act Density 0.217%

    No Known Activations