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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     staying
    -0.09
     improving
    -0.08
     neighboring
    -0.08
    osti
    -0.08
    organized
    -0.07
    indexed
    -0.07
    yet
    -0.07
    క్కువ
    -0.07
    દેશ
    -0.07
    documentation
    -0.07
    POSITIVE LOGITS
     çö
    0.10
     dismissed
    0.10
     Lösungen
    0.09
     discarded
    0.09
     solutions
    0.09
     soluciones
    0.09
    (solution
    0.09
    不得
    0.09
    solutions
    0.09
     বস
    0.08
    Act Density 0.147%

    No Known Activations