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

    Neuronpedia

    INDEX
    Explanations

    for or required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wheat
    0.84
     foodstuffs
    0.76
     wheat
    0.73
     Vegetables
    0.71
     John
    0.68
     terrestrial
    0.68
     Ing
    0.67
     Food
    0.66
     భాగంగా
    0.66
     Sea
    0.66
    POSITIVE LOGITS
    spinlock
    0.65
    把它
    0.63
    stackrel
    0.62
    蹊
    0.62
    これを
    0.61
    ocalypse
    0.61
     делает
    0.60
    ໃຫ
    0.60
     SKAction
    0.59
     }}^{\
    0.59
    Act Density 0.373%

    No Known Activations