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

    Neuronpedia

    INDEX
    Explanations

    MMLU benchmark

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     옆
    0.46
    欧美
    0.45
    ibi
    0.43
    옆
    0.43
    میر
    0.43
     전국
    0.42
    جموعة
    0.41
    pesar
    0.41
     Olímp
    0.41
    óg
    0.41
    POSITIVE LOGITS
    。(
    0.50
     thrombo
    0.47
     xw
    0.46
    一張
    0.43
     warmed
    0.42
     поступ
    0.42
    ្រី
    0.41
     gelten
    0.41
     শিকার
    0.40
    Coordinator
    0.40
    Act Density 0.003%

    No Known Activations