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

    Neuronpedia

    INDEX
    Explanations

    script tag closing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िक
    2.27
    та
    2.25
    тэй
    2.20
    ب
    2.19
    𝕕
    2.05
    ді
    2.03
    ан
    1.93
    로는
    1.91
    дық
    1.91
    ار
    1.91
    POSITIVE LOGITS
    rd
    2.03
    ffen
    2.02
    ra
    1.96
    પણે
    1.88
    ud
    1.86
     DOE
    1.85
    ʽ
    1.82
    쁜
    1.81
    ur
    1.80
    me
    1.80
    Act Density 0.705%

    No Known Activations