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

    Neuronpedia

    INDEX
    Explanations

    but with, I appreciate, a monitor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     niên
    0.48
     numberWith
    0.48
     цилинд
    0.47
     හැ
    0.47
    ógio
    0.47
    োহণ
    0.46
     lĩnh
    0.46
     сексуа
    0.46
    pieceSelection
    0.45
     funções
    0.45
    POSITIVE LOGITS
    X
    0.67
    S
    0.63
    V
    0.62
    P
    0.61
    R
    0.61
    K
    0.61
    IP
    0.60
    N
    0.59
    B
    0.57
    Y
    0.57
    Act Density 0.004%

    No Known Activations