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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "-
    -0.09
    .attributes
    -0.09
     attribut
    -0.09
    attributes
    -0.09
     Attributes
    -0.08
     atribut
    -0.08
     attribution
    -0.08
     attrib
    -0.08
     attributes
    -0.08
     atributos
    -0.08
    POSITIVE LOGITS
     subset
    0.10
     walkway
    0.09
     найд
    0.09
    _subset
    0.08
     monoch
    0.08
    mini
    0.08
     שנים
    0.08
     دهید
    0.08
    най
    0.08
     subse
    0.08
    Act Density 0.033%

    No Known Activations