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

    Neuronpedia

    INDEX
    Explanations

    arrived mechanical behavior preprocessing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -*-č\n
    -0.09
     shemale
    -0.08
    ¶Į
    -0.08
    /devices
    -0.08
    \Dependency
    -0.07
    GLuint
    -0.07
     seedu
    -0.07
    oss
    -0.07
    edula
    -0.07
    vang
    -0.07
    POSITIVE LOGITS
     ï½ľ
    0.07
    DialogContent
    0.07
    -cal
    0.07
    [email
    0.07
    ãĤ
    0.07
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.07
    AdapterManager
    0.07
    .githubusercontent
    0.07
    @Web
    0.07
    .IsNullOr
    0.07
    Act Density 0.427%

    No Known Activations