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

    Neuronpedia

    INDEX
    Explanations

    text passages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    markdown
    -0.08
    enumer
    -0.08
    ursion
    -0.07
    _Mod
    -0.07
     mercy
    -0.07
     investissement
    -0.07
     निष
    -0.07
    -invest
    -0.07
    invest
    -0.07
     justo
    -0.07
    POSITIVE LOGITS
     originates
    0.12
     entstand
    0.11
     vznik
    0.10
     originated
    0.09
     entstanden
    0.09
     berasal
    0.09
     Origin
    0.09
     originate
    0.09
     возникновения
    0.08
     appartient
    0.08
    Act Density 0.163%

    No Known Activations