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

    Neuronpedia

    INDEX
    Explanations

    interests, needs, and welfare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schlüssel
    0.41
    Reception
    0.40
     isot
    0.38
     luckily
    0.38
     reception
    0.37
     associated
    0.37
     receptions
    0.36
     Simply
    0.36
     [[
    0.36
    ptus
    0.36
    POSITIVE LOGITS
     kepentingan
    0.97
    利益
    0.86
     interests
    0.85
     हितों
    0.83
     интере
    0.82
     interessi
    0.81
    interests
    0.80
     intereses
    0.78
     welfare
    0.76
     interesses
    0.75
    Act Density 0.066%

    No Known Activations