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

    Neuronpedia

    INDEX
    Explanations

    describing specific environments or colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     blobs
    0.45
     VERY
    0.44
     Use
    0.44
     gets
    0.43
     use
    0.43
     USED
    0.42
    Use
    0.40
    ボール
    0.39
     máy
    0.39
     govt
    0.38
    POSITIVE LOGITS
     있으며
    0.82
     และ
    0.73
     असून
    0.72
    이며
    0.70
    そして
    0.68
    했고
    0.68
    었고
    0.67
    했으며
    0.66
    ですし
    0.65
     आणि
    0.64
    Act Density 0.155%

    No Known Activations