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

    Neuronpedia

    INDEX
    Explanations

    period punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
    -0.07
    .release
    -0.07
     contest
    -0.07
     stakes
    -0.07
     referred
    -0.07
     grain
    -0.07
     روم
    -0.07
    Medium
    -0.07
     trillion
    -0.07
    estyle
    -0.06
    POSITIVE LOGITS
     ś
    0.06
     Qur
    0.06
     Occ
    0.06
     Lum
    0.06
    TION
    0.06
    -establish
    0.05
    폭
    0.05
     ℕ
    0.05
    izzer
    0.05
     lum
    0.05
    Act Density 0.516%

    No Known Activations