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

    Neuronpedia

    INDEX
    Explanations

    notes and assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    relations
    0.80
     relations
    0.77
     Gre
    0.73
    閆
    0.73
    ณี
    0.72
    した場合
    0.70
    Gre
    0.70
    更高
    0.69
    Relations
    0.69
    uket
    0.68
    POSITIVE LOGITS
    assume
    0.83
    note
    0.79
    ابد
    0.79
     Note
    0.78
    Note
    0.75
     research
    0.74
     assumption
    0.74
     note
    0.71
     assume
    0.71
     assumed
    0.71
    Act Density 0.218%

    No Known Activations