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

    Neuronpedia

    INDEX
    Explanations

    +/-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    damn
    -0.07
    Boundary
    -0.07
     नह
    -0.07
    fake
    -0.07
    _translation
    -0.07
     heartbreaking
    -0.06
     时间
    -0.06
    YSQL
    -0.06
     dakika
    -0.06
    <Option
    -0.06
    POSITIVE LOGITS
     Лит
    0.06
    scss
    0.06
    ,right
    0.06
     retros
    0.06
     Activate
    0.06
     sticky
    0.06
     restaurant
    0.06
     Expl
    0.06
    ufficient
    0.06
     pessoa
    0.06
    Act Density 0.003%

    No Known Activations