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

    Neuronpedia

    INDEX
    Explanations

    HTML tag endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lineContainer
    0.43
     mesma
    0.42
    emphasis
    0.39
     Rhys
    0.39
    <unused429>
    0.38
    <unused1072>
    0.38
     отмеча
    0.36
    LinearLayout
    0.36
     nota
    0.36
    udson
    0.35
    POSITIVE LOGITS
    腦
    0.47
    <span>
    0.46
    Post
    0.41
     ডু
    0.39
    Æ
    0.38
    Გ
    0.38
    Gate
    0.38
     Against
    0.38
    Against
    0.38
    AS
    0.38
    Act Density 0.025%

    No Known Activations