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

    Neuronpedia

    INDEX
    Explanations

    actions and moves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     essentielle
    1.02
    efeu
    0.94
     ebenso
    0.89
    යන්
    0.89
     genug
    0.89
     toekom
    0.89
     genoeg
    0.88
     onge
    0.84
     nieuwe
    0.83
     neben
    0.82
    POSITIVE LOGITS
    a
    0.84
    و
    0.82
    ни
    0.76
    WAY
    0.76
    ه
    0.72
    -
    0.71
    ’
    0.71
    MI
    0.68
    ن
    0.67
    i
    0.66
    Act Density 0.000%

    No Known Activations