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

    Neuronpedia

    INDEX
    Explanations

    study guides and tips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ovsky
    0.74
     Chez
    0.73
     Astral
    0.72
     troca
    0.71
     स्मृति
    0.71
     Keyboard
    0.70
     बैड
    0.70
    swald
    0.70
    Keyboard
    0.68
     hired
    0.68
    POSITIVE LOGITS
    佺
    0.64
     duties
    0.63
     الوس
    0.62
     việc
    0.61
    热水
    0.61
     մի
    0.60
    ecoin
    0.59
    |[
    0.58
     dilemmas
    0.57
     சுவா
    0.57
    Act Density 0.000%

    No Known Activations