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

    Neuronpedia

    INDEX
    Explanations

    youtube channels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    staging
    0.85
    currentState
    0.82
     easiest
    0.78
    stage
    0.76
     них
    0.75
    ходят
    0.74
    similarity
    0.74
    入場
    0.74
    তাদের
    0.74
    セス
    0.72
    POSITIVE LOGITS
    defineProperty
    0.84
     vacuum
    0.70
     دانشگاه
    0.65
     ত্বক
    0.64
     nici
    0.64
     আহম
    0.63
    ลิ
    0.63
    }_
    0.62
     აღ
    0.62
    怎
    0.61
    Act Density 0.013%

    No Known Activations