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

    Neuronpedia

    INDEX
    Explanations

    R

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (async
    -0.08
    IVE
    -0.07
    _clicked
    -0.07
    IGHT
    -0.07
     SCREEN
    -0.06
    Agents
    -0.06
     appDelegate
    -0.06
    lararası
    -0.06
     jokes
    -0.06
     человеч
    -0.06
    POSITIVE LOGITS
     insured
    0.07
    姓名
    0.06
     तहत
    0.06
     DSL
    0.06
     шт
    0.06
     sl
    0.06
     qualquer
    0.06
     Worlds
    0.06
     البلد
    0.06
    Reason
    0.06
    Act Density 0.002%

    No Known Activations