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

    Neuronpedia

    INDEX
    Explanations

    sentences starting a new line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     high
    -0.07
     verbs
    -0.07
     focused
    -0.06
    (instance
    -0.06
    范
    -0.06
    /antlr
    -0.06
    дат
    -0.06
     broad
    -0.06
     Nimbus
    -0.06
     manière
    -0.06
    POSITIVE LOGITS
     Ethan
    0.07
    되는
    0.07
     اک
    0.07
    =====
    0.06
    <W
    0.06
    imately
    0.06
    ').'</
    0.06
    ."[
    0.06
    Γ
    0.06
    .While
    0.06
    Act Density 0.003%

    No Known Activations