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

    Neuronpedia

    INDEX
    Explanations

    piece of, point of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.49
    so
    0.45
    acterial
    0.43
    )\
    0.41
    avoid
    0.41
    referred
    0.41
    mediated
    0.41
    _
    0.40
    '\
    0.40
     відповідно
    0.40
    POSITIVE LOGITS
     시작
    0.42
     모습
    0.39
     camaraderie
    0.39
     progressions
    0.39
     endgame
    0.39
     отказа
    0.38
     predicament
    0.37
     legitim
    0.37
    ილები
    0.36
    ሯ
    0.36
    Act Density 0.060%

    No Known Activations