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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Barbar
    -0.10
     Mart
    -0.09
     বৰ
    -0.08
     থেকেই
    -0.08
     বর
    -0.08
     उत्त
    -0.08
     vermutlich
    -0.08
     Buddhism
    -0.07
     Florian
    -0.07
     Initially
    -0.07
    POSITIVE LOGITS
    죠
    0.08
    .pow
    0.08
     sometimes
    0.08
     usually
    0.08
     keywords
    0.07
    usually
    0.07
     souvent
    0.07
    公式
    0.07
     solved
    0.07
     powered
    0.07
    Act Density 0.144%

    No Known Activations