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

    Neuronpedia

    INDEX
    Explanations

    and,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RestController
    -0.07
    Science
    -0.06
     되어
    -0.06
    alı
    -0.06
     marrying
    -0.06
    半
    -0.06
     recruiters
    -0.06
    Spring
    -0.06
    ible
    -0.06
    setLayout
    -0.06
    POSITIVE LOGITS
    Operator
    0.07
     dissolution
    0.06
     MH
    0.06
     HOR
    0.06
    tabl
    0.06
    sku
    0.06
     SK
    0.06
     LLC
    0.06
    Poor
    0.06
    にお
    0.06
    Act Density 0.071%

    No Known Activations