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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    longitude
    -0.07
    SDK
    -0.07
     acordo
    -0.07
    شمالی
    -0.06
     další
    -0.06
    (lon
    -0.06
     dorsal
    -0.06
    	scroll
    -0.06
    tty
    -0.06
    .verbose
    -0.06
    POSITIVE LOGITS
     Catalonia
    0.06
    بد
    0.06
     pharmacies
    0.06
    .Check
    0.06
     історії
    0.06
     honored
    0.06
    ΗΤ
    0.06
     деревян
    0.06
    �
    0.06
     privileged
    0.06
    Act Density 0.044%

    No Known Activations