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

    Neuronpedia

    INDEX
    Explanations

    configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    穩
    -0.07
    夺取
    -0.07
    韶
    -0.07
    胜任
    -0.07
     nelle
    -0.07
    ựa
    -0.07
     Дан
    -0.07
     menj
    -0.06
     deuxième
    -0.06
     accusations
    -0.06
    POSITIVE LOGITS
    .employee
    0.07
    螱
    0.07
    .created
    0.07
    ']):
    0.07
    眼睛
    0.07
    .Visible
    0.07
    week
    0.06
    .setEmail
    0.06
    ㏂
    0.06
     تاريخ
    0.06
    Act Density 0.025%

    No Known Activations