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

    Neuronpedia

    INDEX
    Explanations

    sentence starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lendir
    0.87
    uta
    0.82
    icier
    0.77
    lint
    0.75
    rement
    0.74
    gos
    0.74
    rosophila
    0.72
    or
    0.72
    cogn
    0.72
    mater
    0.72
    POSITIVE LOGITS
     What
    1.95
     Understanding
    1.86
     How
    1.85
     There
    1.83
     Although
    1.83
     When
    1.82
     This
    1.79
     About
    1.79
     Why
    1.75
     Exploring
    1.75
    Act Density 0.093%

    No Known Activations