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

    Neuronpedia

    INDEX
    Explanations

    Renaissance, Lubricants, behavior, stretching, rub, path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.68
    4
    0.64
    8
    0.63
    5
    0.59
    illiams
    0.56
    bit
    0.54
    6
    0.54
    9
    0.53
     precursors
    0.53
     shepherds
    0.53
    POSITIVE LOGITS
    蘄
    0.54
     perse
    0.51
    리
    0.51
    滹
    0.51
    वाज
    0.49
     animasi
    0.49
     लिप
    0.48
     Plac
    0.48
     อัน
    0.47
     richi
    0.47
    Act Density 0.000%

    No Known Activations