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

    Neuronpedia

    INDEX
    Explanations

    7 followed by 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⇜
    0.40
     mutex
    0.39
     convolution
    0.38
    卷积
    0.37
     bistouri
    0.37
    梯度
    0.36
     apiKey
    0.36
     coseno
    0.36
     dueDate
    0.35
     contractName
    0.35
    POSITIVE LOGITS
    7
    0.42
    )
    0.38
    ).
    0.36
    0.35
    4
    0.35
    6
    0.35
    8
    0.35
    ft
    0.33
    3
    0.33
    )(-
    0.32
    Act Density 0.012%

    No Known Activations