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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orias
    -0.08
    ("")
    -0.07
     ماه
    -0.07
    mae
    -0.07
    indr
    -0.06
     Guerr
    -0.06
    sstream
    -0.06
     miser
    -0.06
    �m
    -0.06
    üş
    -0.06
    POSITIVE LOGITS
     amber
    0.07
    ///
↵
    0.07
     Yu
    0.06
    ======
    0.06
     bulbs
    0.06
     towering
    0.06
    　　　　　　　　　　
    0.06
     regarded
    0.06
     ):↵
    0.06
    _TX
    0.06
    Act Density 0.000%

    No Known Activations