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

    Neuronpedia

    INDEX
    Explanations

    document snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     firewall
    -0.07
    VICES
    -0.07
    erator
    -0.06
    .ConnectionStrings
    -0.06
     داشته
    -0.06
    퓨
    -0.06
    .Runtime
    -0.06
     break
    -0.06
    Tensor
    -0.06
     snad
    -0.06
    POSITIVE LOGITS
    auto
    0.07
    OST
    0.07
     murdering
    0.06
     Virgin
    0.06
     Mult
    0.06
    /l
    0.06
    Equ
    0.06
     Final
    0.06
    ordial
    0.06
    koneksi
    0.06
    Act Density 0.000%

    No Known Activations