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

    Neuronpedia

    INDEX
    Explanations

    CSRF and CSP security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    喬
    0.45
     Brod
    0.41
     filtra
    0.38
    мона
    0.38
     agres
    0.37
    複雑
    0.37
     Brodie
    0.37
    跋
    0.37
     скла
    0.36
    แมนเชสเตอร์ซิตี
    0.36
    POSITIVE LOGITS
     CSR
    0.73
    CSR
    0.72
     csr
    0.64
    csrf
    0.60
     CSP
    0.55
    Cs
    0.54
     csp
    0.52
     csrf
    0.52
     CSI
    0.51
    CSP
    0.51
    Act Density 0.000%

    No Known Activations