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

    Neuronpedia

    INDEX
    Explanations

    seeking enrollment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     é
    0.63
     ryzy
    0.63
     ash
    0.62
     बन
    0.62
     Ash
    0.61
     latach
    0.61
     हादसा
    0.61
     þe
    0.60
    નારા
    0.59
    िंक
    0.59
    POSITIVE LOGITS
     নবী
    0.73
    Electronics
    0.71
    Usually
    0.71
     nose
    0.71
     rosto
    0.68
    guests
    0.67
    पहर
    0.66
    œurs
    0.66
     نا
    0.65
     ఇంటి
    0.65
    Act Density 0.000%

    No Known Activations