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

    Neuronpedia

    INDEX
    Explanations

    python code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    拜
    0.63
    enties
    0.61
    ddots
    0.60
    ழ
    0.59
    ying
    0.57
     trap
    0.56
    Professor
    0.55
     jang
    0.55
     മൂല
    0.54
    ொழுது
    0.54
    POSITIVE LOGITS
    ದಾ
    0.69
    age
    0.69
    aron
    0.69
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.69
    Dockerfile
    0.68
    oko
    0.68
    โค
    0.67
     बेर
    0.67
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.66
    ocurrency
    0.66
    Act Density 0.407%

    No Known Activations