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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    umba
    -0.07
     DVDs
    -0.06
     Wolves
    -0.06
     du
    -0.06
    ffect
    -0.06
     gall
    -0.06
     rivers
    -0.06
    _ON
    -0.06
    prites
    -0.06
    POSITIVE LOGITS
     î
    0.07
     """
↵
↵
    0.07
     трен
    0.07
     rychle
    0.07
    ersen
    0.06
    ,,,
    0.06
    VISION
    0.06
    ##↵↵
    0.06
    ']↵↵
    0.06
     انت
    0.06
    Act Density 0.000%

    No Known Activations