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

    Neuronpedia

    INDEX
    Explanations

    time durations like hour

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    শীল
    0.41
     개념
    0.41
    ertain
    0.40
    ereal
    0.39
    ests
    0.38
     posee
    0.38
     conceptos
    0.37
    풀
    0.37
    razione
    0.37
    AVER
    0.36
    POSITIVE LOGITS
     thermally
    0.41
     nymphs
    0.40
     maintained
    0.39
     emptying
    0.39
     Andes
    0.38
    احت
    0.38
     autoclave
    0.37
     torture
    0.37
     TORT
    0.37
    ভু
    0.37
    Act Density 0.000%

    No Known Activations