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

    Neuronpedia

    INDEX
    Explanations

    deepfakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    旻
    0.80
    centric
    0.76
    etera
    0.75
    kách
    0.74
    éral
    0.72
    ppermint
    0.72
    icut
    0.71
    elift
    0.71
    ključ
    0.70
     देवगन
    0.70
    POSITIVE LOGITS
    mfrac
    0.78
    зі
    0.78
    frac
    0.69
     ১২
    0.68
     네
    0.66
    💞
    0.66
    Δ
    0.66
    ♥️
    0.65
     Δ
    0.64
    ffineTransform
    0.63
    Act Density 0.014%

    No Known Activations