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

    Neuronpedia

    INDEX
    Explanations

    collapse and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    渀
    0.38
     MUL
    0.38
     Rog
    0.36
     डिट
    0.36
    zter
    0.36
    ഊ
    0.36
    Rog
    0.35
     Cena
    0.34
    骡
    0.34
    elijkheid
    0.34
    POSITIVE LOGITS
     collapse
    3.89
     collapsed
    3.70
     collapses
    3.56
     Collapse
    3.56
    collapse
    3.50
     collapsing
    3.41
    Collapse
    3.34
    collapsed
    3.05
    Collapsed
    2.80
     collapsible
    2.55
    Act Density 0.049%

    No Known Activations