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

    Neuronpedia

    INDEX
    Explanations

    explaining options, concepts, or prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     errMsg
    0.46
     mensal
    0.45
    ]<<
    0.44
    ুতরাং
    0.44
    れている
    0.44
    警
    0.43
    臺灣
    0.42
     variáveis
    0.42
    葆
    0.42
     అంది
    0.42
    POSITIVE LOGITS
    ۔
    0.52
    ف
    0.49
     Kiz
    0.48
    ments
    0.47
    otel
    0.47
    ।
    0.44
    weed
    0.44
    agons
    0.44
    ویز
    0.44
    way
    0.43
    Act Density 0.001%

    No Known Activations