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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نو
    -0.06
    =cv
    -0.06
    syn
    -0.06
    iêu
    -0.06
    徒歩
    -0.06
    stride
    -0.06
    _runner
    -0.05
     )
↵
↵
    -0.05
     senha
    -0.05
     ster
    -0.05
    POSITIVE LOGITS
     noticeably
    0.08
     And
    0.08
    And
    0.07
     Skate
    0.07
     Breaking
    0.07
     sanat
    0.07
     and
    0.07
    †
    0.07
     nutné
    0.06
    減
    0.06
    Act Density 0.421%

    No Known Activations