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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )?
    -0.08
    การ
    -0.08
     özellikle
    -0.08
    人们
    -0.08
    表达
    -0.08
    ᴳ
    -0.07
    ')).
    -0.07
    主帅
    -0.07
    Future
    -0.07
     pioneers
    -0.07
    POSITIVE LOGITS
     Á
    0.07
    aqu
    0.07
    azzi
    0.07
    华丽
    0.07
     �
    0.07
    abil
    0.07
    urn
    0.06
    _procs
    0.06
    \API
    0.06
    iam
    0.06
    Act Density 0.013%

    No Known Activations