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

    Neuronpedia

    INDEX
    Explanations

    encoding scheme, directly shape, automate tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    6
    0.52
    Environment
    0.46
    5
    0.45
    传输
    0.45
    CUSSION
    0.44
    ど
    0.44
    กับ
    0.43
    4
    0.42
    ์
    0.41
    Technische
    0.41
    POSITIVE LOGITS
    vene
    0.45
     skin
    0.45
     amor
    0.45
     ADHD
    0.45
     sunflowers
    0.45
    ior
    0.44
     Stonehenge
    0.44
    jene
    0.44
     shreds
    0.44
     uso
    0.43
    Act Density 0.018%

    No Known Activations