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

    Neuronpedia

    INDEX
    Explanations

    Congratulations and well-wishes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riad
    -0.08
    violent
    -0.08
    徴
    -0.08
    _cod
    -0.07
    Trip
    -0.07
     differs
    -0.07
    amiliar
    -0.07
     vary
    -0.07
    Programming
    -0.07
    Viol
    -0.07
    POSITIVE LOGITS
     wonderfully
    0.11
     wünsche
    0.10
     accomplishments
    0.10
     adorable
    0.10
     �
    0.10
     awesome
    0.10
     😊
    0.10
     wunderbar
    0.10
    abéns
    0.10
     Ehr
    0.09
    Act Density 0.039%

    No Known Activations