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

    Neuronpedia

    INDEX
    Explanations

    Vulkan renderer, GUI toolkit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    øy
    0.45
     Cel
    0.43
    utus
    0.40
     Getter
    0.39
    rierung
    0.39
     Darling
    0.38
    ңү
    0.38
     Ace
    0.38
    astal
    0.38
    鍗
    0.37
    POSITIVE LOGITS
    നേ
    0.43
    defining
    0.40
    beginning
    0.40
    textepsilon
    0.39
     mul
    0.38
     ቀ
    0.38
    elements
    0.38
     começo
    0.37
    Elementos
    0.37
    intercept
    0.37
    Act Density 0.000%

    No Known Activations