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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ު
    0.43
    🕑
    0.43
     FontWeight
    0.42
    stateMutability
    0.42
    🚍
    0.40
    🕙
    0.39
    🕔
    0.39
    🚱
    0.38
     RenderTexture
    0.38
    ष
    0.37
    POSITIVE LOGITS
    temp
    0.97
     temp
    0.91
     tmp
    0.89
    tmp
    0.87
    foo
    0.82
     foo
    0.82
     x
    0.82
     xxx
    0.77
    value
    0.75
    x
    0.75
    Act Density 0.130%

    No Known Activations