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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wrap
    0.41
     wrap
    0.40
    wrap
    0.40
    chol
    0.38
     버튼
    0.37
    Wrap
    0.37
    trust
    0.37
    button
    0.37
    grid
    0.37
     wrapping
    0.37
    POSITIVE LOGITS
    usahaan
    0.46
    સ્ક
    0.43
     analogy
    0.42
    企業の
    0.42
     formalism
    0.40
     Jeong
    0.39
     skinned
    0.39
     informativo
    0.38
     പ്രച
    0.38
     ইহ
    0.38
    Act Density 0.000%

    No Known Activations