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

    Neuronpedia

    INDEX
    Explanations

    chess moves notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lblCredits
    0.39
    MDEw
    0.39
    뺻
    0.38
    पोरेशन
    0.38
    脌
    0.38
    瓴
    0.38
    ोध्या
    0.37
     बजाज
    0.37
     ڈپاز
    0.37
    ังสือ
    0.37
    POSITIVE LOGITS
    0.50
    4
    0.47
    3
    0.46
    2
    0.44
    5
    0.44
    1
    0.42
     R
    0.41
    R
    0.39
    7
    0.39
    6
    0.38
    Act Density 0.001%

    No Known Activations