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

    Neuronpedia

    INDEX
    Explanations

    't

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Você
    -0.07
     confidently
    -0.07
    GameState
    -0.07
    兰
    -0.07
     tane
    -0.07
     کمی
    -0.07
    Effective
    -0.07
    718
    -0.07
     abundance
    -0.06
    باز
    -0.06
    POSITIVE LOGITS
    siyon
    0.07
    (',');↵
    0.07
    arsing
    0.06
    ophobia
    0.06
     storage
    0.06
    .domain
    0.06
     Steel
    0.06
    picable
    0.06
     personal
    0.06
     garment
    0.06
    Act Density 0.014%

    No Known Activations