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

    Neuronpedia

    INDEX
    Explanations

    programming import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.77
    ↵↵↵
    0.75
    </li>
    0.70
    㐹
    0.68
    blueberry
    0.68
     ;)
    0.66
    㐱
    0.66
    joke
    0.65
     eureka
    0.65
     Brahmin
    0.64
    POSITIVE LOGITS
     container
    0.84
     Container
    0.74
    ở
    0.73
     isolation
    0.72
    Container
    0.71
     به
    0.71
     suprem
    0.70
    ాలని
    0.70
    ches
    0.70
    рому
    0.69
    Act Density 0.062%

    No Known Activations