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

    Neuronpedia

    INDEX
    Explanations

    supply, dose, flux, fuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     வீ
    0.45
     اص
    0.44
    rique
    0.43
    ianic
    0.43
     ويكيپيديا
    0.42
    rette
    0.42
     Y
    0.41
    lict
    0.41
    imet
    0.41
    ences
    0.41
    POSITIVE LOGITS
     Candles
    0.55
    އ
    0.52
     vested
    0.52
     worry
    0.51
    mnopqr
    0.50
    ガネ
    0.49
     devam
    0.49
     hobby
    0.49
    ﮐ
    0.49
     Unemployment
    0.48
    Act Density 0.000%

    No Known Activations