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

    Neuronpedia

    INDEX
    Explanations

    denounce harmful concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    已
    0.47
     jeweils
    0.44
     or
    0.44
     Real
    0.43
     lags
    0.42
    Real
    0.41
     And
    0.41
     rés
    0.41
     real
    0.41
    开
    0.41
    POSITIVE LOGITS
    adaya
    0.54
    asta
    0.52
    chee
    0.50
    വ്ര
    0.48
     एमसीक्यू
    0.47
    thione
    0.46
    chman
    0.46
    ম্ত
    0.46
    hitva
    0.46
     ठहर
    0.46
    Act Density 0.020%

    No Known Activations