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

    Neuronpedia

    INDEX
    Explanations

    and data or collaborate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    1.09
    1
    1.06
    7
    1.01
    3
    0.98
    6
    0.98
    5
    0.95
    2
    0.93
    8
    0.92
    9
    0.89
    か
    0.80
    POSITIVE LOGITS
     whatnot
    0.79
     Subsidi
    0.71
    ּ
    0.66
    খানেই
    0.64
    ப்பட்ட
    0.64
    :‏
    0.62
    ndash
    0.60
     goddesses
    0.58
    珅
    0.58
     وعلى
    0.57
    Act Density 1.935%

    No Known Activations