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

    Neuronpedia

    INDEX
    Explanations

    thoughts of harm or danger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ackerel
    0.68
     from
    0.67
     refreshments
    0.66
     convenience
    0.65
     fittings
    0.65
    ová
    0.64
     stationery
    0.64
     conveniences
    0.64
     Fittings
    0.64
     earrings
    0.63
    POSITIVE LOGITS
     totalitarian
    0.91
     subversive
    0.91
     terrifying
    0.86
    spiracy
    0.86
     obses
    0.81
     psychedelic
    0.80
     peligros
    0.80
     cosidd
    0.79
     hallucin
    0.79
     berbahaya
    0.75
    Act Density 0.000%

    No Known Activations