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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     supremacy
    -0.07
     failure
    -0.06
     Begins
    -0.06
     bibli
    -0.06
     rocked
    -0.06
    ंट
    -0.06
     Overrides
    -0.06
    Universal
    -0.06
    .Empty
    -0.06
    Error
    -0.06
    POSITIVE LOGITS
     ”↵↵
    0.06
    情報
    0.06
    _TIM
    0.06
     uptime
    0.06
    _valor
    0.06
     Maver
    0.06
     　　　
    0.06
    _ads
    0.06
    >'+↵
    0.06
    codegen
    0.06
    Act Density 0.042%

    No Known Activations