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

    Neuronpedia

    INDEX
    Explanations

    Swagger API documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    0.94
    0.81
    的海
    0.70
    .
    0.68
    )
    0.68
     How
    0.67
    AB
    0.67
     I
    0.64
    的孩子
    0.64
     You
    0.63
    POSITIVE LOGITS
    openapi
    0.77
    ić
    0.75
    Swagger
    0.75
    ות
    0.74
     বসব
    0.73
    FileList
    0.72
    که
    0.72
    to
    0.71
    enapi
    0.70
    <unused2183>
    0.70
    Act Density 0.005%

    No Known Activations