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

    Neuronpedia

    INDEX
    Explanations

    code syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ర్జ
    0.53
    类型
    0.47
     ores
    0.46
    ⌵
    0.45
    েক
    0.44
    ଟି
    0.44
     impuestos
    0.44
     rhino
    0.44
    䀎
    0.43
    స్
    0.43
    POSITIVE LOGITS
    }.
    0.55
    ''.
    0.49
    }"
    0.49
    ."
    0.47
    ".
    0.44
    :
    0.44
    .),
    0.44
    ."))
    0.44
    und
    0.43
    )".
    0.43
    Act Density 0.376%

    No Known Activations