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

    Neuronpedia

    INDEX
    Explanations

    hypotheticals, numbers, or specific actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     swipes
    0.55
     Alford
    0.48
    తున్నాయి
    0.48
     లె
    0.47
     Petrol
    0.47
     collapsing
    0.46
     IncludeField
    0.46
     జీ
    0.45
     زائدا
    0.45
     Dö
    0.45
    POSITIVE LOGITS
    인
    0.50
    вер
    0.49
     octombrie
    0.48
     satunya
    0.47
    anjutan
    0.46
    ры
    0.46
    graduation
    0.46
    night
    0.45
    نی
    0.45
     parti
    0.45
    Act Density 0.000%

    No Known Activations