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

    Neuronpedia

    INDEX
    Explanations

    -F

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DEFINED
    -0.07
    feof
    -0.06
     Lah
    -0.06
     Went
    -0.06
     Sew
    -0.06
     Hew
    -0.06
     �
    -0.06
     Rin
    -0.06
     aus
    -0.06
     inflict
    -0.06
    POSITIVE LOGITS
    SM
    0.07
     scoring
    0.07
     aiding
    0.07
    _engine
    0.06
     contribute
    0.06
     action
    0.06
     mobility
    0.06
     фін
    0.06
    경기
    0.06
    具体
    0.06
    Act Density 0.000%

    No Known Activations