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

    Neuronpedia

    INDEX
    Explanations

    contrasting or listing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Aquatic
    0.39
    参赛
    0.38
    詄
    0.38
    ސ
    0.37
     intérieure
    0.36
    𠄌
    0.36
     dwRes
    0.35
    …</
    0.34
    shot
    0.34
    సింది
    0.34
    POSITIVE LOGITS
    ropol
    0.41
    Bootstrap
    0.39
     monomials
    0.39
    Weber
    0.38
    gravity
    0.38
    عبة
    0.38
    本の
    0.38
    beste
    0.38
     evaporates
    0.37
    Jenkins
    0.37
    Act Density 0.000%

    No Known Activations