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

    Neuronpedia

    INDEX
    Explanations

    tippaleipä

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    针对
    0.38
    mittance
    0.36
    min
    0.34
     transfer
    0.34
    瑠
    0.34
    hd
    0.34
     suficientemente
    0.34
     retrospect
    0.33
     retir
    0.33
     internally
    0.33
    POSITIVE LOGITS
    aus
    0.68
    auks
    0.65
    AUS
    0.57
    ari
    0.57
    arit
    0.57
    arima
    0.57
    auk
    0.54
    ARI
    0.52
    Aus
    0.52
    AU
    0.52
    Act Density 0.001%

    No Known Activations