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

    Neuronpedia

    INDEX
    Explanations

    Code with symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     tiểu
    -0.07
     **************************************************************************
    -0.07
    沈
    -0.07
    _index
    -0.06
    ，您
    -0.06
     cuffs
    -0.06
    .caption
    -0.06
    October
    -0.06
    -0.06
    POSITIVE LOGITS
    vely
    0.08
    electric
    0.07
    λε
    0.07
     Bucks
    0.06
     Dun
    0.06
     adultery
    0.06
    vé
    0.06
    дя
    0.06
    입
    0.06
     Kare
    0.06
    Act Density 0.055%

    No Known Activations