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

    Neuronpedia

    INDEX
    Explanations

    known

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ग्रह
    -0.08
     rätt
    -0.08
     hot
    -0.08
    નની
    -0.07
     बनाने
    -0.07
    न्त
    -0.07
    ನಾ
    -0.07
     оф
    -0.07
    shown
    -0.07
     Kevin
    -0.07
    POSITIVE LOGITS
     interv
    0.08
    有关
    0.08
     vak
    0.08
     влияние
    0.07
    特点
    0.07
    关于
    0.07
     sache
    0.07
     различные
    0.07
     চাল
    0.07
    JR
    0.07
    Act Density 0.007%

    No Known Activations