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

    Neuronpedia

    INDEX
    Explanations

    .security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     měla
    -0.07
     suf
    -0.07
    _root
    -0.07
     εί
    -0.06
    zan
    -0.06
     Kosten
    -0.06
    ủng
    -0.06
     Stud
    -0.06
     Sub
    -0.06
     Rust
    -0.06
    POSITIVE LOGITS
    '],$_
    0.07
     UserProfile
    0.07
    ...',
    0.07
    authority
    0.06
     Reviews
    0.06
     Gender
    0.06
     auth
    0.06
     inplace
    0.06
    columns
    0.06
     marrow
    0.06
    Act Density 0.002%

    No Known Activations