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

    Neuronpedia

    INDEX
    Explanations

    fan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Component
    -0.07
     bearings
    -0.07
     crafts
    -0.07
     Divide
    -0.06
     Suite
    -0.06
    Certificates
    -0.06
    udu
    -0.06
     effectively
    -0.06
    Touches
    -0.06
     move
    -0.06
    POSITIVE LOGITS
     fans
    0.09
     fan
    0.09
     Fan
    0.08
     Fans
    0.08
    Fans
    0.08
    iosk
    0.07
    ﾉ
    0.07
    Fan
    0.07
     luckily
    0.07
     ans
    0.07
    Act Density 0.009%

    No Known Activations