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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    سلام
    -0.07
    asan
    -0.07
     Assurance
    -0.06
    ону
    -0.06
     نوش
    -0.06
    anoia
    -0.06
     ranks
    -0.06
     isp
    -0.06
     discourse
    -0.06
    浮
    -0.06
    POSITIVE LOGITS
               
↵
    0.07
    �
    0.07
    (Id
    0.07
    hh
    0.07
    ۲۶
    0.06
    .bp
    0.06
     &(
    0.06
    acağ
    0.06
    =[[
    0.06
            ↵↵
    0.06
    Act Density 0.003%

    No Known Activations