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

    Neuronpedia

    INDEX
    Explanations

    CWE and vulnerabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఆదాయ
    0.42
     vertebr
    0.40
    </bbox>
    0.40
    Scroll
    0.39
     kamer
    0.39
    猊
    0.38
    ळं
    0.38
    Orden
    0.38
    溲
    0.38
     ಗುರು
    0.38
    POSITIVE LOGITS
     vulnerabilities
    0.52
     misuse
    0.52
     uses
    0.52
     vulner
    0.50
     vulnerability
    0.50
     vulnerable
    0.48
     flaw
    0.47
     flawed
    0.47
     use
    0.47
     CWE
    0.46
    Act Density 0.000%

    No Known Activations