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

    Neuronpedia

    INDEX
    Explanations

    indicate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    قام
    -0.07
    璺
    -0.07
    墁
    -0.07
    块
    -0.07
    墙上
    -0.07
    陷入了
    -0.07
    _DOM
    -0.07
     Wak
    -0.07
    teste
    -0.07
    Bits
    -0.07
    POSITIVE LOGITS
    、「
    0.07
    URLConnection
    0.06
    .Experimental
    0.06
     וזה
    0.06
     conception
    0.06
    .onDestroy
    0.06
     =================
    0.06
    「
    0.06
    ":"
    0.06
     Geoffrey
    0.06
    Act Density 0.004%

    No Known Activations