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

    Neuronpedia

    INDEX
    Explanations

    CRUD

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocy
    -0.08
    Kİ
    -0.07
    𝐗
    -0.07
    sed
    -0.07
    (Cs
    -0.07
     estos
    -0.07
    战略布局
    -0.07
    icens
    -0.07
     بأ
    -0.07
    _kv
    -0.07
    POSITIVE LOGITS
    ᨹ
    0.07
    
    0.07
    灾难
    0.07
    难忘
    0.06
    现阶段
    0.06
     BigDecimal
    0.06
    usiness
    0.06
    姈
    0.06
    edelta
    0.06
    har
    0.06
    Act Density 0.004%

    No Known Activations