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

    Neuronpedia

    INDEX
    Explanations

    various options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आणि
    0.73
     અને
    0.65
    每年
    0.64
     ਅਤੇ
    0.64
     ಮತ್ತು
    0.61
     nascita
    0.60
     seraient
    0.59
     annuelle
    0.59
     vivent
    0.59
     mécan
    0.58
    POSITIVE LOGITS
    J
    0.55
    様々な
    0.54
     Various
    0.54
    Verbose
    0.54
     various
    0.53
    Variants
    0.52
     heuristics
    0.52
     subtlety
    0.52
     çeşitli
    0.51
     Attempts
    0.51
    Act Density 0.927%

    No Known Activations