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

    Neuronpedia

    INDEX
    Explanations

    adjust path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Techn
    0.72
     Marijuana
    0.72
     Move
    0.72
     Myths
    0.71
     Neighbor
    0.70
     Forum
    0.69
     Notch
    0.68
     Again
    0.68
     AGAIN
    0.68
    詮
    0.67
    POSITIVE LOGITS
    value
    0.81
    zio
    0.81
    ibr
    0.79
    Crawler
    0.77
    collapse
    0.76
    Deletion
    0.75
    Integration
    0.73
    optimal
    0.73
    Braun
    0.73
    Optimal
    0.73
    Act Density 0.002%

    No Known Activations