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

    Neuronpedia

    INDEX
    Explanations

    explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.88
     during
    0.86
     +
    0.78
     и
    0.74
    そして
    0.74
    的同时
    0.72
     along
    0.72
    ²,
    0.71
     &&
    0.71
     և
    0.71
    POSITIVE LOGITS
     necessariamente
    0.76
     solchen
    0.69
    某种
    0.68
     necesariamente
    0.66
    DeleteDialogOpen
    0.65
     अपनाने
    0.65
     특정
    0.64
    agamanam
    0.64
     raczej
    0.64
    逭
    0.64
    Act Density 0.000%

    No Known Activations