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

    Neuronpedia

    INDEX
    Explanations

    after "He" climbed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ok
    0.48
    oh
    0.44
    ad
    0.44
    ro
    0.44
    be
    0.44
    oben
    0.43
    ot
    0.43
     Effect
    0.43
    effect
    0.42
    ai
    0.41
    POSITIVE LOGITS
     landfills
    0.51
    ヴィトン
    0.48
     Fleurit
    0.47
     உணர
    0.47
     tolerances
    0.46
     individuo
    0.46
    ೫
    0.46
     unstructured
    0.46
     ateliers
    0.46
    љено
    0.45
    Act Density 0.005%

    No Known Activations