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

    Neuronpedia

    INDEX
    Explanations

    securing resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     മേഖ
    0.49
     maliciously
    0.48
     szé
    0.46
     viy
    0.46
     pernicious
    0.46
     savk
    0.45
    ".*:
    0.44
     án
    0.44
     obscurity
    0.44
     trúc
    0.44
    POSITIVE LOGITS
    दोस्तों
    0.47
    au
    0.43
    nagar
    0.41
    ยนต์
    0.41
    ku
    0.40
    SU
    0.40
    ua
    0.40
     synergies
    0.39
    us
    0.38
    nect
    0.38
    Act Density 0.001%

    No Known Activations