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

    Neuronpedia

    INDEX
    Explanations

    Entities, components, concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Suggestion
    0.43
    كت
    0.42
     fraction
    0.41
     libro
    0.41
    rological
    0.41
    著作
    0.41
    碛
    0.41
     Suggest
    0.41
    днев
    0.40
     ocurr
    0.39
    POSITIVE LOGITS
     biom
    0.47
    มัน
    0.47
     dach
    0.47
    kannya
    0.47
    inas
    0.46
     thân
    0.46
    ມັນ
    0.46
    ită
    0.45
    ukes
    0.45
    žený
    0.45
    Act Density 0.004%

    No Known Activations