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

    Neuronpedia

    INDEX
    Explanations

    not X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    0.38
     ihrer
    0.35
    ov
    0.33
    ie
    0.32
    in
    0.31
    o
    0.31
     refers
    0.31
     oth
    0.31
     tzv
    0.30
    iv
    0.30
    POSITIVE LOGITS
     heartache
    0.33
    机遇
    0.33
    革命
    0.32
    ETS
    0.31
    स्मै
    0.30
     exhilar
    0.30
    많은
    0.30
     समझिए
    0.29
    唆
    0.29
     downright
    0.29
    Act Density 0.185%

    No Known Activations