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

    Neuronpedia

    INDEX
    Explanations

    opposition prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Segments
    0.91
     AFFAIRS
    0.90
     झालेल्या
    0.89
    AppDesigner
    0.88
    ኀ
    0.85
     liable
    0.84
    ช่วย
    0.83
     Fixing
    0.83
     buộc
    0.83
     setActive
    0.83
    POSITIVE LOGITS
    clockwise
    0.71
     lại
    0.69
    dote
    0.63
     tive
    0.62
    inflammatory
    0.61
    imes
    0.60
    вес
    0.60
    woorden
    0.59
    ive
    0.59
    pm
    0.58
    Act Density 0.103%

    No Known Activations