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

    Neuronpedia

    INDEX
    Explanations

    SIEM: Security Information and Event Management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RE
    0.58
     nä
    0.55
     Icelandic
    0.47
     vaca
    0.47
    കളിൽ
    0.46
     recycler
    0.46
     LS
    0.46
     lä
    0.46
     दिवस
    0.46
     reais
    0.46
    POSITIVE LOGITS
    C
    0.62
    &
    0.55
    ansk
    0.54
    rue
    0.53
    Bor
    0.52
    Eigen
    0.50
    精灵
    0.50
    Herd
    0.50
    ربه
    0.50
    Replacing
    0.49
    Act Density 0.004%

    No Known Activations