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

    Neuronpedia

    INDEX
    Explanations

    business or self-improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,)
    -0.07
    十六
    -0.07
    ,class
    -0.06
    ,
↵
    -0.06
    .decoder
    -0.06
     исследования
    -0.06
    _RGCTX
    -0.06
     pornos
    -0.06
     fried
    -0.06
     характеристики
    -0.06
    POSITIVE LOGITS
    题
    0.06
     blankets
    0.06
     {}'.
    0.06
     지난
    0.06
    竹
    0.06
     TIMEOUT
    0.06
     Encyclopedia
    0.06
     exceedingly
    0.06
    .parseInt
    0.06
    emaakt
    0.06
    Act Density 0.288%

    No Known Activations