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

    Neuronpedia

    INDEX
    Explanations

    Dockerfile instructions and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    okin
    0.78
     Taunton
    0.77
     meteor
    0.77
    ចុ
    0.75
    hau
    0.74
    meteor
    0.73
    ев
    0.69
    ikawa
    0.69
    ៃ
    0.68
     caoutchouc
    0.68
    POSITIVE LOGITS
     Lenovo
    0.85
     Colbert
    0.83
     Sen
    0.80
     Colon
    0.77
     Colón
    0.75
    Len
    0.74
     Jenner
    0.73
     Col
    0.71
    Sentinel
    0.71
    Dockerfile
    0.70
    Act Density 0.238%

    No Known Activations