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

    Neuronpedia

    INDEX
    Explanations

    names of people and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    q
    -2.94
    3
    -2.92
    if
    -2.91
    7
    -2.91
    It
    -2.77
    5
    -2.72
    4
    -2.70
    9
    -2.69
    8
    -2.67
    AL
    -2.59
    POSITIVE LOGITS
    詒
    2.86
     causado
    2.84
     faſt
    2.81
    賡
    2.81
    ﾍ
    2.63
    玳
    2.53
    牁
    2.50
     Bereichen
    2.48
     DEPOSIT
    2.47
    ikusbot
    2.47
    Act Density 0.020%

    No Known Activations