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

    Neuronpedia

    INDEX
    Explanations

    cancel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ses
    -0.07
     mol
    -0.06
    findOne
    -0.06
     testimony
    -0.06
     buf
    -0.06
     scream
    -0.06
    цю
    -0.06
    bcd
    -0.06
     sor
    -0.05
    “For
    -0.05
    POSITIVE LOGITS
     Dickinson
    0.07
    爱
    0.07
     عبارت
    0.07
     newPassword
    0.07
    .setCharacter
    0.07
     khởi
    0.07
     sodium
    0.07
     Savaşı
    0.06
    ↵    ↵
    0.06
    .)↵↵
    0.06
    Act Density 0.001%

    No Known Activations