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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ཚ
    -0.08
     qb
    -0.08
     rang
    -0.07
    飓
    -0.06
     ath
    -0.06
    swith
    -0.06
    𝙺
    -0.06
    青春
    -0.06
    甜甜
    -0.06
    ϑ
    -0.06
    POSITIVE LOGITS
    [text
    0.07
     backing
    0.07
    ival
    0.07
    鼗
    0.07
    (as
    0.07
     addTarget
    0.06
    !(
    0.06
     "")
    0.06
     contexto
    0.06
     Solar
    0.06
    Act Density 0.008%

    No Known Activations