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

    Neuronpedia

    INDEX
    Explanations

    environment variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    쎌
    0.43
    <0xBA>
    0.42
     разви
    0.39
    ายน
    0.39
    stateMutability
    0.39
    嶈
    0.38
    ตรวจสอบ
    0.38
    лан
    0.37
    科学家
    0.37
     %+
    0.37
    POSITIVE LOGITS
    েক্টর
    0.40
    Hyp
    0.39
     sant
    0.36
    Fest
    0.36
     wore
    0.35
    stoff
    0.35
    aufnahme
    0.35
    DEVICE
    0.35
    Bru
    0.35
     file
    0.35
    Act Density 0.000%

    No Known Activations