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

    Neuronpedia

    INDEX
    Explanations

    letters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﮅ
    0.63
     multicultural
    0.54
     ‎
    0.54
     horsepower
    0.53
     cybersecurity
    0.52
     RMSE
    0.52
     fintech
    0.52
     postmodern
    0.52
     piercings
    0.52
     ‏
    0.51
    POSITIVE LOGITS
    L
    0.57
    I
    0.56
    N
    0.56
    T
    0.54
    E
    0.53
    W
    0.52
    C
    0.52
    Y
    0.51
    O
    0.50
    F
    0.50
    Act Density 0.217%

    No Known Activations