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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Presidency
    -0.08
     Norfolk
    -0.07
    ンド
    -0.07
     publications
    -0.07
     BufferedImage
    -0.07
    nc
    -0.07
     Invite
    -0.07
    Stand
    -0.07
    监狱
    -0.07
     Superintendent
    -0.06
    POSITIVE LOGITS
    밍
    0.07
    quivo
    0.07
     frau
    0.06
     arriv
    0.06
    систем
    0.06
    ([↵
    0.06
    izacao
    0.06
    .lineEdit
    0.06
     אירועים
    0.06
     shemale
    0.06
    Act Density 0.017%

    No Known Activations