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

    Neuronpedia

    INDEX
    Explanations

    distance or length

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    灑
    0.43
     mivel
    0.43
    以外の
    0.42
     funktion
    0.41
     lång
    0.41
     ય
    0.41
    ㄜ
    0.41
     Ə
    0.41
    だけの
    0.41
     vita
    0.40
    POSITIVE LOGITS
    1
    0.50
    quoted
    0.49
    enabled
    0.49
    4
    0.47
    one
    0.47
    с
    0.46
    were
    0.46
    inv
    0.45
    6
    0.45
     Corea
    0.45
    Act Density 0.004%

    No Known Activations