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

    Neuronpedia

    INDEX
    Explanations

    explicit male genitalia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lagoons
    0.40
     Volta
    0.39
    鎏
    0.38
    lcl
    0.38
     zonal
    0.37
     Rum
    0.37
    𝐯
    0.37
     Galveston
    0.36
     VMware
    0.36
     somm
    0.36
    POSITIVE LOGITS
     penis
    1.38
     dick
    1.34
    Dick
    1.20
     Penis
    1.18
     DICK
    1.15
    Penis
    1.12
    dick
    1.05
     Dick
    1.04
     cock
    0.97
     dik
    0.85
    Act Density 0.061%

    No Known Activations