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

    Neuronpedia

    INDEX
    Explanations

    contrast or concession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    磵
    0.45
    ERSON
    0.44
     marketplaces
    0.44
    èles
    0.41
     MERC
    0.41
     wafers
    0.40
    ди
    0.40
     hybrids
    0.39
    ült
    0.38
     человека
    0.38
    POSITIVE LOGITS
     being
    0.79
    being
    0.78
     despite
    0.72
    despite
    0.70
     étant
    0.66
    in
    0.66
    Despite
    0.66
     Despite
    0.64
    having
    0.63
     having
    0.61
    Act Density 0.010%

    No Known Activations