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

    Neuronpedia

    INDEX
    Explanations

    above

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    piar
    -0.08
    ח
    -0.07
     Kind
    -0.07
    听
    -0.07
    لفة
    -0.07
     enter
    -0.07
     mã
    -0.07
    Speed
    -0.07
    ectors
    -0.07
    Sound
    -0.06
    POSITIVE LOGITS
     above
    0.12
    above
    0.10
     below
    0.09
     Above
    0.09
     ABOVE
    0.08
    below
    0.08
     strive
    0.08
     Below
    0.07
    ELLOW
    0.07
    Above
    0.07
    Act Density 0.059%

    No Known Activations