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

    Neuronpedia

    INDEX
    Explanations

    harmful or criminality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     documentación
    0.40
     charging
    0.39
    腩
    0.39
     சீன
    0.39
     Charging
    0.38
     нагру
    0.38
    Eras
    0.38
    documentation
    0.37
     GIFs
    0.37
     பஞ்ச
    0.37
    POSITIVE LOGITS
     antisocial
    1.17
     psychopath
    1.06
     criminal
    1.00
     pathology
    0.99
     criminality
    0.99
    criminal
    0.90
     pathological
    0.89
    Criminal
    0.87
     Antis
    0.87
     deviant
    0.87
    Act Density 0.034%

    No Known Activations