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

    Neuronpedia

    INDEX
    Explanations

    criticism or things being overrated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    羿
    0.40
     забе
    0.39
     pTM
    0.39
    ixi
    0.38
    PreviewSize
    0.37
    osum
    0.37
    ->_
    0.37
    樞
    0.37
     機
    0.36
    חוז
    0.36
    POSITIVE LOGITS
     overrated
    1.84
     overpriced
    1.62
     hype
    1.16
     hyped
    1.12
     overestimated
    1.06
     inflated
    1.02
     overstated
    1.01
     expensive
    0.99
     mediocre
    0.95
     mediocr
    0.94
    Act Density 0.015%

    No Known Activations