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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ئات
    -0.08
    Can't
    -0.08
    十四
    -0.07
     СО
    -0.07
    _connection
    -0.07
     fourteen
    -0.07
    ван
    -0.07
    _application
    -0.07
     CONNECTION
    -0.07
    ій
    -0.07
    POSITIVE LOGITS
     petals
    0.08
     여러
    0.08
     Nearby
    0.08
     breaths
    0.08
     հաջ
    0.08
     nearby
    0.08
     subsequent
    0.08
     meerdere
    0.08
    两个
    0.08
     ڈال
    0.08
    Act Density 0.497%

    No Known Activations