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

    Neuronpedia

    INDEX
    Explanations

    related to numbers and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     알파
    0.36
     alarma
    0.35
     FFT
    0.34
     FF
    0.34
    Ｐ
    0.33
     ALPHA
    0.33
     spf
    0.32
     fft
    0.32
     anise
    0.32
     männ
    0.31
    POSITIVE LOGITS
     vast
    0.34
    vast
    0.31
    uth
    0.28
     glorify
    0.28
    URY
    0.28
    unov
    0.28
    ur
    0.27
     gas
    0.27
     largely
    0.27
     مقصد
    0.27
    Act Density 0.002%

    No Known Activations