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

    Neuronpedia

    INDEX
    Explanations

    fence, fencing, fenced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    彣
    -3.25
    The
    -3.09
    ”
    -2.78
    甡
    -2.64
    नलोड
    -2.48
    From
    -2.48
    In
    -2.42
    幃
    -2.39
     –
    -2.38
    翼翼
    -2.38
    POSITIVE LOGITS
    崀
    3.14
    <bos>
    2.39
    )
    2.33
     efectivos
    2.28
     conocidas
    2.25
     invitar
    2.25
    不论
    2.22
     preocupar
    2.20
    茕
    2.20
    王的
    2.19
    Act Density 0.005%

    No Known Activations