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

    Neuronpedia

    INDEX
    Explanations

    structured explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Madd
    1.45
    Mar
    1.39
     Mar
    1.38
    mar
    1.36
     fix
    1.34
     bread
    1.32
     resolved
    1.32
     cafe
    1.32
     HTML
    1.31
     MAR
    1.29
    POSITIVE LOGITS
    Penumpang
    0.81
    IIUM
    0.78
    赝
    0.73
    <end_of_image>
    0.72
     Blazers
    0.71
    NonUser
    0.71
     TestAvg
    0.70
     Skate
    0.68
     Stairs
    0.68
    運行
    0.66
    Act Density 0.279%

    No Known Activations