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

    Neuronpedia

    INDEX
    Explanations

    say "pm"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Directories
    -0.08
    ивання
    -0.08
    weed
    -0.07
    @Inject
    -0.07
     สาข
    -0.07
    (td
    -0.07
    eds
    -0.06
    於
    -0.06
     pope
    -0.06
     Sexy
    -0.06
    POSITIVE LOGITS
     Forbidden
    0.06
    reek
    0.06
    IVING
    0.06
    „M
    0.05
    สง
    0.05
     thỏa
    0.05
    μα
    0.05
     감사
    0.05
     ;;=
    0.05
     sản
    0.05
    Act Density 0.019%

    No Known Activations