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

    Neuronpedia

    INDEX
    Explanations

    sounds like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "...
    -0.07
    jah
    -0.07
     Европ
    -0.06
    ,...↵↵
    -0.06
     eternal
    -0.06
    TITLE
    -0.06
    BASEPATH
    -0.06
    oston
    -0.06
    jdbc
    -0.06
    سمة
    -0.06
    POSITIVE LOGITS
    Section
    0.07
     problema
    0.07
    тон
    0.06
     beau
    0.06
     ka
    0.06
    /cmd
    0.06
    _DS
    0.06
     combine
    0.06
    构
    0.06
    .active
    0.06
    Act Density 0.047%

    No Known Activations