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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Amount
    -0.06
    ")]↵
    -0.06
     Eag
    -0.06
    iphers
    -0.06
    BE
    -0.06
    );↵↵↵
    -0.06
    Hugh
    -0.06
    StatusLabel
    -0.06
     Albany
    -0.06
    Acceler
    -0.06
    POSITIVE LOGITS
    emme
    0.06
    desk
    0.06
    ắn
    0.06
    .^
    0.06
     رسید
    0.06
    .ic
    0.06
    보내기
    0.06
    だろう
    0.06
    ogra
    0.06
     دید
    0.06
    Act Density 0.037%

    No Known Activations