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

    Neuronpedia

    INDEX
    Explanations

    mathematical and programming lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বিনিম
    0.41
     \(
    0.40
    ᐉ
    0.39
     outflow
    0.39
     Mantra
    0.39
    =[
    0.38
    汚
    0.37
     Contribution
    0.36
     poisoned
    0.36
     DC
    0.36
    POSITIVE LOGITS
     рассчиты
    0.49
    路線
    0.46
    लाइ
    0.45
    lees
    0.44
     आमच्या
    0.44
    जीत
    0.42
    лып
    0.42
     нала
    0.42
     joked
    0.42
     খবর
    0.41
    Act Density 0.000%

    No Known Activations