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

    Neuronpedia

    INDEX
    Explanations

    state descriptions after "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    еты
    0.68
    ットフォーム
    0.68
     สืบค้น
    0.67
     piatta
    0.66
     የሚ
    0.65
    पुढे
    0.64
     viện
    0.63
     lather
    0.63
    юд
    0.63
    ሲ
    0.63
    POSITIVE LOGITS
     spot
    0.96
     move
    0.84
     inside
    0.83
     way
    0.83
     Spot
    0.80
     Spots
    0.79
    Spot
    0.78
     fly
    0.75
     Move
    0.75
     contrary
    0.75
    Act Density 0.051%

    No Known Activations