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

    Neuronpedia

    INDEX
    Explanations

    Time references in multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     factorial
    -0.07
    忘
    -0.07
     fog
    -0.06
     cafe
    -0.06
     enjoyment
    -0.06
     presente
    -0.06
     moderated
    -0.06
    оп
    -0.06
    	GL
    -0.06
    “But
    -0.06
    POSITIVE LOGITS
     DOI
    0.06
    abilirsiniz
    0.06
     Leonardo
    0.06
    .Checked
    0.06
     Stanley
    0.06
    ocommerce
    0.06
    丝
    0.06
    mov
    0.06
    cmpeq
    0.06
     kapsam
    0.06
    Act Density 0.000%

    No Known Activations