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

    Neuronpedia

    INDEX
    Explanations

    describing components and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    te
    0.57
    ir
    0.55
    n
    0.53
    ton
    0.52
    and
    0.50
    r
    0.50
    g
    0.50
    dan
    0.50
    ten
    0.49
    gaz
    0.49
    POSITIVE LOGITS
     হাসপাত
    0.49
     sanitizer
    0.49
     দুর্যোগ
    0.48
     McDermott
    0.46
    让她
    0.46
    쯜
    0.46
    夯
    0.45
     multiport
    0.45
     प्रस्ताव
    0.45
    度假
    0.44
    Act Density 0.001%

    No Known Activations