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

    Neuronpedia

    INDEX
    Explanations

    at the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     நாடுகளில்
    0.16
    !
    0.16
     eller
    0.15
    ;
    0.15
     vatten
    0.15
     fries
    0.15
     meeste
    0.14
     yoki
    0.14
     tämän
    0.14
     tohoto
    0.14
    POSITIVE LOGITS
     꾸
    0.15
     insidious
    0.14
    regular
    0.13
     пути
    0.13
    蝌
    0.13
     diffuse
    0.13
    ದ್ದ
    0.13
     uncanny
    0.13
    उंड
    0.13
     lowly
    0.13
    Act Density 0.228%

    No Known Activations