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

    Neuronpedia

    INDEX
    Explanations

    define

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     predictive
    -0.06
     Tyler
    -0.06
    .port
    -0.06
     kararı
    -0.06
     Mojo
    -0.06
    91
    -0.06
     AMAZ
    -0.06
    體
    -0.06
     trucks
    -0.06
    POSITIVE LOGITS
     define
    0.08
     Define
    0.07
     Play
    0.06
    utf
    0.06
    .Le
    0.06
     Choi
    0.06
    'eau
    0.06
    ンド
    0.06
    unny
    0.06
    }->{
    0.06
    Act Density 0.017%

    No Known Activations