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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     richly
    -0.08
    终于
    -0.08
    然
    -0.07
     Aristotle
    -0.07
    �
    -0.07
     vaguely
    -0.07
    所
    -0.07
    惨
    -0.07
    secutive
    -0.07
     funded
    -0.07
    POSITIVE LOGITS
     redesign
    0.12
     تعديل
    0.11
     ajustar
    0.11
     workaround
    0.11
     ajust
    0.11
     либо
    0.10
     adjust
    0.10
     Adjust
    0.10
    _adjust
    0.10
    Adjust
    0.10
    Act Density 0.037%

    No Known Activations