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

    Neuronpedia

    INDEX
    Explanations

    futanari or programming assertions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mga
    0.72
     Toolkit
    0.71
     Secure
    0.70
     Async
    0.69
     Backend
    0.68
     Namespace
    0.68
     Dropout
    0.67
    '){$
    0.67
     Lifecycle
    0.67
     Diver
    0.67
    POSITIVE LOGITS
    ing
    0.91
    er
    0.83
    ched
    0.81
    ucle
    0.78
    oring
    0.77
    ings
    0.76
    ometrical
    0.76
    ishment
    0.75
    ger
    0.75
    ling
    0.75
    Act Density 0.291%

    No Known Activations