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

    Neuronpedia

    INDEX
    Explanations

    Academic concepts and learning strategies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ल
    1.17
    en
    1.13
    ला
    1.10
    es
    1.07
    л
    1.06
    ాను
    1.06
    𝘬
    1.05
    ی
    1.04
    Fermi
    1.04
    इंडिया
    1.03
    POSITIVE LOGITS
    undang
    1.21
    酈
    1.18
     हराकर
    1.15
     käyt
    1.12
    記事
    1.08
    veriş
    1.06
    جراء
    1.05
    ról
    1.04
    rahman
    1.04
    tól
    1.04
    Act Density 0.000%

    No Known Activations