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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Spring
    -0.07
     růz
    -0.06
    edral
    -0.06
    .Dispatcher
    -0.06
    ="#">
    -0.06
    Geometry
    -0.06
    ฑ
    -0.06
    estado
    -0.06
    --)
↵
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     takım
    0.07
     JOHN
    0.07
     Evolution
    0.06
     είχαν
    0.06
     delightful
    0.06
    Poor
    0.06
    賽
    0.06
    AZE
    0.06
     #"
    0.06
     degli
    0.06
    Act Density 0.024%

    No Known Activations