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

    Neuronpedia

    INDEX
    Explanations

    step

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    maker
    -0.07
    WRITE
    -0.06
    зи
    -0.06
    VISIBLE
    -0.06
    Česk
    -0.06
     Curriculum
    -0.06
     interests
    -0.06
     bleiben
    -0.06
    nummer
    -0.06
     contentType
    -0.06
    POSITIVE LOGITS
     step
    0.07
    циклоп
    0.07
     steps
    0.06
     وإ
    0.06
     Kemal
    0.06
    <dim
    0.06
    姑
    0.06
     progressively
    0.06
     м
    0.06
    發展
    0.06
    Act Density 0.021%

    No Known Activations