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

    Neuronpedia

    INDEX
    Explanations

    react render updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ълга
    0.76
    roz
    0.76
     roz
    0.69
     expandable
    0.67
     expanded
    0.65
     groin
    0.65
     экза
    0.64
     expanding
    0.64
    लिप
    0.63
    潰
    0.63
    POSITIVE LOGITS
     reactivity
    1.19
     reactive
    1.08
     реак
    1.08
    Render
    1.02
    Reactive
    1.00
     render
    0.99
     rendering
    0.99
     Reactive
    0.98
     updates
    0.96
     Updates
    0.94
    Act Density 0.220%

    No Known Activations