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

    Neuronpedia

    INDEX
    Explanations

    how and what questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.33
    if
    1.26
    StatusCode
    1.25
     नतीजा
    1.15
    ie
    1.14
    Probably
    1.12
    uite
    1.10
    Mere
    1.09
    Collapse
    1.08
    𝒊
    1.08
    POSITIVE LOGITS
    ные
    1.39
    ных
    1.37
     geschikt
    1.28
     créer
    1.28
     endow
    1.27
     shaders
    1.25
     관한
    1.24
    ductory
    1.23
     orthonormal
    1.22
    withstanding
    1.21
    Act Density 0.276%

    No Known Activations