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

    Neuronpedia

    INDEX
    Explanations

    understandingtheconcepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hogwarts
    0.89
     Dura
    0.84
     relevancia
    0.84
     Brad
    0.84
     Silverado
    0.83
    რთ
    0.83
    žila
    0.83
     luces
    0.82
     Sundance
    0.82
    いっぱい
    0.80
    POSITIVE LOGITS
     segue
    0.66
     bagay
    0.65
    ાલ
    0.65
     frowned
    0.64
    REACTOR
    0.63
    av
    0.63
    ence
    0.62
    село
    0.62
    RICH
    0.60
    幄
    0.59
    Act Density 0.000%

    No Known Activations