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

    Neuronpedia

    INDEX
    Explanations

    options ranging in formality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.52
    !=
    0.50
    le
    0.49
     ℝ
    0.48
    s
    0.47
    Segmentation
    0.46
    _
    0.46
    ==
    0.46
    XE
    0.45
    :
    0.45
    POSITIVE LOGITS
     দেহের
    0.45
    avaş
    0.45
     вероят
    0.45
     authorise
    0.45
     improb
    0.44
     probabilidad
    0.44
    शरी
    0.44
     descenso
    0.44
    iovas
    0.43
    ಗೊಳ
    0.43
    Act Density 0.004%

    No Known Activations