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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infert
    -0.09
     insignificant
    -0.09
     irres
    -0.09
     erection
    -0.09
     PSU
    -0.09
     heterosexual
    -0.08
     indiv
    -0.08
     Inches
    -0.08
     іст
    -0.08
     üh
    -0.08
    POSITIVE LOGITS
    营销
    0.12
     newsletters
    0.11
    渠道
    0.10
     marketing
    0.10
     webinars
    0.10
     podcasts
    0.10
     outreach
    0.10
     livestream
    0.10
     storytelling
    0.10
     सोशल
    0.10
    Act Density 0.034%

    No Known Activations