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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks/colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tested
    -0.06
     cooler
    -0.06
     золот
    -0.06
    HIGH
    -0.06
    λώ
    -0.06
     menace
    -0.06
    长度
    -0.06
     needing
    -0.06
    睡
    -0.06
     Wilhelm
    -0.06
    POSITIVE LOGITS
     Citizens
    0.07
    .randomUUID
    0.07
    [NUM
    0.06
    (bucket
    0.06
    _Rel
    0.06
     ExecutionContext
    0.06
    $username
    0.06
    γνω
    0.06
     culturally
    0.06
    [${
    0.06
    Act Density 0.004%

    No Known Activations