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
    _;
↵
    -0.07
     Voj
    -0.07
    悉
    -0.07
     Bread
    -0.06
     obvious
    -0.06
     Commander
    -0.06
    亮
    -0.06
    wx
    -0.06
    .exports
    -0.06
    modules
    -0.06
    POSITIVE LOGITS
     béné
    0.07
    -thinking
    0.07
     SOC
    0.06
     Friends
    0.06
    QS
    0.06
     Supervisor
    0.06
    Compatible
    0.06
     deductions
    0.06
    İL
    0.06
    0.06
    Act Density 0.017%

    No Known Activations