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

    Neuronpedia

    INDEX
    Explanations

    malware prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chirurg
    0.52
     ब्रांच
    0.51
    ởi
    0.45
    伢
    0.44
     Gyne
    0.43
    けば
    0.42
     Prussians
    0.42
     Surgeon
    0.41
    ల్యే
    0.41
     introduit
    0.40
    POSITIVE LOGITS
    Level
    0.52
    ↵↵↵
    0.51
    level
    0.48
    Prediction
    0.47
    size
    0.45
    prediction
    0.45
    Wave
    0.43
    pred
    0.43
    مر
    0.42
    Crystal
    0.42
    Act Density 0.004%

    No Known Activations