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

    Neuronpedia

    INDEX
    Explanations

    no hesitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WHO
    0.41
     WHO
    0.39
     online
    0.39
     Vera
    0.39
     Selling
    0.39
    yyyy
    0.38
     Historical
    0.37
     Online
    0.37
     IUCN
    0.37
     Terra
    0.36
    POSITIVE LOGITS
     quelconque
    0.51
     передви
    0.44
     അറ
    0.44
     ergeben
    0.42
     quelcon
    0.41
     уро
    0.41
     gages
    0.40
    ぞれ
    0.40
     これらの
    0.39
     коман
    0.39
    Act Density 0.000%

    No Known Activations