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

    Neuronpedia

    INDEX
    Explanations

    "exactly one" logic problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    紙
    -0.08
     alternate
    -0.08
    don
    -0.07
     pay
    -0.07
    elsey
    -0.07
     же
    -0.07
    set
    -0.07
     medic
    -0.07
     California
    -0.06
     начала
    -0.06
    POSITIVE LOGITS
     überhaupt
    0.10
     comprehensive
    0.09
     tällä
    0.09
    prehensive
    0.09
     encima
    0.09
    <Long
    0.08
     sèl
    0.08
     sequer
    0.08
     plethora
    0.08
     einzige
    0.08
    Act Density 0.055%

    No Known Activations