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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disaster
    -0.08
     agricultural
    -0.07
    Pool
    -0.07
     Laundry
    -0.06
    food
    -0.06
    (Field
    -0.06
    ندان
    -0.06
     skulls
    -0.06
    queeze
    -0.06
    feed
    -0.06
    POSITIVE LOGITS
     문의
    0.07
    _wr
    0.06
     zest
    0.06
     ре
    0.06
    ->[
    0.06
    	sem
    0.06
    半
    0.06
     ofere
    0.06
     언제
    0.06
     момент
    0.06
    Act Density 0.006%

    No Known Activations