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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    圙
    -0.07
     <!--<
    -0.07
    =('
    -0.07
    곘
    -0.07
    üß
    -0.07
     Def
    -0.06
     Aless
    -0.06
    emies
    -0.06
    hole
    -0.06
    珲
    -0.06
    POSITIVE LOGITS
     usability
    0.08
    -lined
    0.07
    队长
    0.07
    Seconds
    0.07
     UserRole
    0.07
    אולי
    0.07
     schw
    0.07
    וויר
    0.07
     viper
    0.07
    _take
    0.07
    Act Density 0.003%

    No Known Activations