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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .yellow
    -0.07
    智
    -0.07
    .decorators
    -0.06
    夫
    -0.06
     百度
    -0.06
     inactive
    -0.06
    ecx
    -0.06
     scam
    -0.06
    ,x
    -0.06
    Former
    -0.06
    POSITIVE LOGITS
    ْح
    0.07
    relude
    0.07
    deniz
    0.07
    (Image
    0.06
    eygamber
    0.06
    elsea
    0.06
     sponsorship
    0.06
    )↵↵↵↵↵↵
    0.06
    _DL
    0.06
     demonstrators
    0.06
    Act Density 0.003%

    No Known Activations