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

    Neuronpedia

    INDEX
    Explanations

    code logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wie
    -0.07
     sigma
    -0.07
     Heat
    -0.06
     kou
    -0.06
    cal
    -0.06
     쓰
    -0.06
    Energy
    -0.06
    Kar
    -0.06
    Heat
    -0.06
    žit
    -0.06
    POSITIVE LOGITS
    .Dict
    0.07
     천
    0.06
    _video
    0.06
    تن
    0.06
    าจารย
    0.06
    ossed
    0.06
    рес
    0.06
    .ActionEvent
    0.06
    ι
    0.06
     CSRF
    0.06
    Act Density 0.035%

    No Known Activations