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

    Neuronpedia

    INDEX
    Explanations

    urls ending in html

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Romantic
    0.71
     Kategorie
    0.70
     Gourmet
    0.68
     Romantic
    0.63
     Strawberry
    0.62
    旅游
    0.61
     Honey
    0.61
     Dinosaur
    0.60
    Master
    0.59
    Travelling
    0.59
    POSITIVE LOGITS
     quotas
    0.65
     missiles
    0.62
     weeds
    0.61
     quos
    0.60
    arul
    0.60
     indices
    0.59
     billions
    0.59
     amplitudes
    0.59
     arbitrage
    0.58
    vspace
    0.58
    Act Density 0.000%

    No Known Activations