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

    Neuronpedia

    INDEX
    Explanations

    onion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     πρα
    -0.08
     flee
    -0.07
    lara
    -0.07
    193
    -0.07
     здійсню
    -0.07
     попада
    -0.07
    esse
    -0.07
     vacations
    -0.07
    fare
    -0.07
     формування
    -0.06
    POSITIVE LOGITS
     onion
    0.12
     Onion
    0.12
     onions
    0.10
     Ink
    0.08
     Cork
    0.07
    있는
    0.07
     mushrooms
    0.07
    (rowIndex
    0.07
     underneath
    0.07
     Ginger
    0.06
    Act Density 0.002%

    No Known Activations