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

    Neuronpedia

    INDEX
    Explanations

    fine

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    repent
    0.67
    োর্ট
    0.66
    ributor
    0.66
     Reform
    0.66
    cdf
    0.65
    ircle
    0.65
    lies
    0.64
     inhe
    0.63
    elect
    0.63
     INCIDENTAL
    0.62
    POSITIVE LOGITS
     tuning
    1.93
     tune
    1.91
     Tuning
    1.89
     tuned
    1.88
    tuning
    1.70
    tune
    1.61
     Tune
    1.59
    tuned
    1.57
     tunes
    1.54
    Tune
    1.52
    Act Density 0.017%

    No Known Activations