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

    Neuronpedia

    INDEX
    Explanations

    banking trojan WAS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BINARY
    0.42
    介绍
    0.40
    Synopsis
    0.40
     व्हाइट
    0.40
     giản
    0.39
    𝘐
    0.39
    ৌশ
    0.38
    Credit
    0.37
    𝐈
    0.37
    “”
    0.37
    POSITIVE LOGITS
     blisters
    0.39
     freezer
    0.38
     sickness
    0.38
     premiums
    0.37
    sten
    0.37
     tiles
    0.37
    stones
    0.37
     wounds
    0.36
     inco
    0.35
     web
    0.35
    Act Density 0.001%

    No Known Activations