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

    Neuronpedia

    INDEX
    Explanations

    parenthetical phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Harold
    0.40
    Prot
    0.39
    Sale
    0.38
     bourbon
    0.38
    Foe
    0.38
    傣
    0.38
    Tec
    0.37
     Harold
    0.37
     Nobel
    0.37
    Drone
    0.37
    POSITIVE LOGITS
     Audience
    0.43
    減少
    0.42
     concom
    0.41
     محور
    0.39
     Decre
    0.38
    regator
    0.38
    mediation
    0.38
     Pagination
    0.37
     decreases
    0.37
    闔
    0.37
    Act Density 0.002%

    No Known Activations