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

    Neuronpedia

    INDEX
    Explanations

    mathematical reasoning and hypotheticals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     पड
    -0.08
     Seam
    -0.08
     обознач
    -0.08
    的吗
    -0.08
     Lovely
    -0.08
    atsen
    -0.08
     linestyle
    -0.08
     nomen
    -0.08
     पुष
    -0.07
     officially
    -0.07
    POSITIVE LOGITS
     large
    0.12
     dominating
    0.12
     dominate
    0.12
     huge
    0.11
     quickly
    0.11
     rapidly
    0.11
     aggressively
    0.10
     enormous
    0.10
     concentrated
    0.10
     aggressive
    0.10
    Act Density 0.049%

    No Known Activations