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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     analys
    -0.07
     Thanksgiving
    -0.07
    蓓
    -0.07
    詳
    -0.07
    �
    -0.07
    ffl
    -0.07
     �
    -0.07
    孬
    -0.06
    .rstrip
    -0.06
     ARTICLE
    -0.06
    POSITIVE LOGITS
    isoner
    0.08
    inem
    0.07
    нят
    0.07
    IJ
    0.06
    🍙
    0.06
     payout
    0.06
    ㄍ
    0.06
    jadi
    0.06
    czeń
    0.06
    ほど
    0.06
    Act Density 0.068%

    No Known Activations