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

    Neuronpedia

    INDEX
    Explanations

    logic conditions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ian
    0.50
     عَل
    0.47
     يح
    0.44
    0.44
     كوب
    0.44
     وإن
    0.43
     الف
    0.43
    ART
    0.42
    PLAN
    0.42
     كوس
    0.42
    POSITIVE LOGITS
     ru
    0.53
     contained
    0.52
     ruin
    0.49
     riv
    0.49
     Oyun
    0.47
     included
    0.47
     documented
    0.47
     zostały
    0.46
    ，
    0.46
     cmd
    0.45
    Act Density 0.000%

    No Known Activations