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

    Neuronpedia

    INDEX
    Explanations

    periods and multiples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    improve
    0.51
    icare
    0.47
     دی
    0.47
     വൃ
    0.46
    पथ
    0.46
    瘪
    0.45
     veteran
    0.45
    купа
    0.45
    یک
    0.44
    pilot
    0.44
    POSITIVE LOGITS
     aggrav
    0.43
     প্রতিদিন
    0.42
    ￩
    0.41
     ਤੁਹਾ
    0.40
     samtid
    0.40
     procesos
    0.39
    ljiv
    0.39
     agrav
    0.39
     tâches
    0.39
     ইমন
    0.38
    Act Density 0.000%

    No Known Activations