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
    _Ass
    -0.07
    钚
    -0.07
    🧁
    -0.07
    饱满
    -0.06
    𝚋
    -0.06
    :convert
    -0.06
     Pillow
    -0.06
    去哪里
    -0.06
    onz
    -0.06
     relinqu
    -0.06
    POSITIVE LOGITS
    RIPTION
    0.07
    律
    0.07
    छ
    0.07
    .Bottom
    0.07
    �述
    0.07
     IV
    0.07
    _rt
    0.07
    member
    0.07
    十三条
    0.06
    itical
    0.06
    Act Density 0.047%

    No Known Activations