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

    Neuronpedia

    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ْف
    -0.07
     fora
    -0.07
     Todos
    -0.06
    олов
    -0.06
     vont
    -0.06
     Fairy
    -0.06
     yaw
    -0.06
     ==↵
    -0.06
    _click
    -0.06
    蛋
    -0.06
    POSITIVE LOGITS
     incomplete
    0.07
    ('</
    0.06
    juries
    0.06
    (categories
    0.06
    มหานคร
    0.06
     span
    0.06
     installed
    0.06
     backstage
    0.06
    (constants
    0.06
    modifiable
    0.06
    Act Density 0.000%

    No Known Activations