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

    Neuronpedia

    INDEX
    Explanations

    suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kris
    -0.07
    ContentAlignment
    -0.07
     priest
    -0.07
    оре
    -0.06
     charter
    -0.06
    _absolute
    -0.06
     xd
    -0.06
    Password
    -0.06
    chair
    -0.06
     plaza
    -0.06
    POSITIVE LOGITS
    uffix
    0.07
    Buff
    0.06
    就是
    0.06
    Suffix
    0.06
    .DotNetBar
    0.06
     postfix
    0.06
    lazy
    0.06
     moduleName
    0.06
    _hooks
    0.06
     =========================================================================
    0.06
    Act Density 0.005%

    No Known Activations