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

    Neuronpedia

    INDEX
    Explanations

    underrated, undervalued, underhyped

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಪಟ್ಟ
    0.66
     reag
    0.66
     Kommun
    0.64
     टेल
    0.64
     spectrogram
    0.64
    िटीज
    0.63
     vipp
    0.63
     Bhagav
    0.62
    ામ
    0.61
    ف
    0.61
    POSITIVE LOGITS
     underrated
    0.93
     underestimated
    0.88
    .
    0.86
     underestimate
    0.77
    eração
    0.65
     overrated
    0.65
     undervalued
    0.61
    র
    0.61
    arında
    0.60
    قیه
    0.60
    Act Density 0.005%

    No Known Activations