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

    Neuronpedia

    INDEX
    Explanations

    math and physics notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dimethyl
    0.46
    ValueOf
    0.43
     लैंग्वे
    0.43
    ethoscope
    0.42
    ጴ
    0.41
    鑾
    0.40
    ProductRunnable
    0.39
    ๊ก
    0.39
    溴
    0.38
    リング
    0.38
    POSITIVE LOGITS
     sight
    0.42
    服
    0.39
    vista
    0.38
     subs
    0.38
     serving
    0.37
     Freedom
    0.37
     ആദ്യം
    0.37
    ritt
    0.37
     torsion
    0.36
     freedom
    0.35
    Act Density 0.000%

    No Known Activations