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

    Neuronpedia

    INDEX
    Explanations

    as a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blew
    -0.30
     Blow
    -0.26
    amera
    -0.26
    REW
    -0.25
    便åı¯
    -0.25
    Republic
    -0.24
    .alias
    -0.24
    disabled
    -0.24
    untlet
    -0.24
     Downing
    -0.24
    POSITIVE LOGITS
    pair
    0.28
    ÃŃn
    0.27
     Basis
    0.26
    íĨµìĭł
    0.25
    ials
    0.25
    óst
    0.25
     tats
    0.25
    ä¸Ģ代
    0.25
    åĨį度
    0.24
    xin
    0.24
    Act Density 28.889%

    No Known Activations