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
    实现
    -0.07
     Ś
    -0.06
    Sc
    -0.06
    thesis
    -0.06
    .this
    -0.06
    ra
    -0.06
    姓
    -0.06
     echang
    -0.06
    erox
    -0.06
     façon
    -0.06
    POSITIVE LOGITS
     Bowen
    0.07
    plemented
    0.07
    Paid
    0.07
    阳台
    0.07
    Disabled
    0.07
    onne
    0.07
    onium
    0.07
     ReferentialAction
    0.06
    דות
    0.06
    主城区
    0.06
    Act Density 0.007%

    No Known Activations