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

    Neuronpedia

    INDEX
    Explanations

    fat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tuto
    -0.06
    kul
    -0.06
     bene
    -0.06
     meetings
    -0.06
     amazon
    -0.06
    (states
    -0.06
    areas
    -0.06
    “Our
    -0.06
    ipur
    -0.06
    やす
    -0.06
    POSITIVE LOGITS
     금
    0.07
    ّة
    0.07
    пис
    0.06
    <=
    0.06
    си
    0.06
    0.06
    0.06
    0.06
     lng
    0.06
    /kubernetes
    0.06
    Act Density 0.002%

    No Known Activations