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

    Neuronpedia

    INDEX
    Explanations

    e

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    መር
    1.03
    asmim
    0.97
     ケース
    0.92
     advogado
    0.89
    ólica
    0.89
    țele
    0.88
    gleichen
    0.88
    迨
    0.87
    ólico
    0.87
     Riz
    0.86
    POSITIVE LOGITS
    𝙚
    0.78
     conduits
    0.75
     επί
    0.74
     gla
    0.74
     encourages
    0.70
    grasp
    0.68
    fast
    0.67
    WAYS
    0.67
    ways
    0.65
    slide
    0.65
    Act Density 0.010%

    No Known Activations