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

    Neuronpedia

    INDEX
    Explanations

    internalizing into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Laver
    0.42
    毯
    0.38
     jeśli
    0.38
     campaigning
    0.38
     آیا
    0.38
     ambulatory
    0.37
     conical
    0.37
     Transparency
    0.37
     كلكم
    0.37
     bowl
    0.37
    POSITIVE LOGITS
     toep
    0.38
    在本
    0.36
    日本
    0.36
     wɔ
    0.35
    殊
    0.35
    یاط
    0.34
    μο
    0.34
    holders
    0.33
    使用
    0.33
     ahli
    0.32
    Act Density 0.001%

    No Known Activations