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

    Neuronpedia

    INDEX
    Explanations

    safe space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Delgado
    0.70
     menging
    0.65
    DrawerToggle
    0.65
    嗝
    0.64
    Liens
    0.64
     solvency
    0.63
    </footer>
    0.63
    astava
    0.62
     gait
    0.61
     কাটিয়ে
    0.60
    POSITIVE LOGITS
     space
    1.95
     spaces
    1.90
     safe
    1.87
     Space
    1.75
     espacio
    1.72
    Space
    1.72
     espacios
    1.69
    Safe
    1.69
     Safe
    1.68
    space
    1.67
    Act Density 0.429%

    No Known Activations