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

    Neuronpedia

    INDEX
    Explanations

    understand language models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AssetsResponse
    0.45
     pacientes
    0.42
     이용
    0.42
     libre
    0.41
     pergunta
    0.41
     hỏi
    0.40
     pede
    0.40
     gpointer
    0.40
     पूर्वक
    0.40
    手术
    0.39
    POSITIVE LOGITS
    fighting
    0.50
    Serv
    0.47
    American
    0.46
    general
    0.45
    Kot
    0.43
    General
    0.43
    Fighting
    0.41
    6
    0.41
    await
    0.41
    Castle
    0.41
    Act Density 0.000%

    No Known Activations