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

    Neuronpedia

    INDEX
    Explanations

    Blogger post IDs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     catapult
    -0.07
    rieving
    -0.07
    🏽
    -0.07
     Julian
    -0.07
    itmap
    -0.07
    loys
    -0.07
    OneToMany
    -0.07
     móg
    -0.06
    illi
    -0.06
    targets
    -0.06
    POSITIVE LOGITS
     Adolescent
    0.07
     Coupon
    0.07
     Discount
    0.07
     steals
    0.07
     Piece
    0.07
    .Ass
    0.07
     free
    0.07
     Außen
    0.07
    对外开放
    0.07
    캡
    0.07
    Act Density 0.002%

    No Known Activations