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

    Neuronpedia

    INDEX
    Explanations

    tools &

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.48
    IN
    0.41
    ς
    0.40
     globe
    0.40
     Number
    0.39
     מח
    0.39
     logistical
    0.39
     Constitution
    0.38
    <0x0D>
    0.38
     city
    0.38
    POSITIVE LOGITS
    ب
    0.69
    ৮
    0.63
    it
    0.61
     оборудование
    0.55
    ography
    0.55
    ो
    0.53
    ৫
    0.53
    icionado
    0.50
    အစိတ်အပိုင်း
    0.49
    and
    0.48
    Act Density 0.353%

    No Known Activations