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

    Neuronpedia

    INDEX
    Explanations

    definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invasion
    -0.07
     seminal
    -0.07
     roles
    -0.07
     můž
    -0.06
     stej
    -0.06
     PhD
    -0.06
    -0.06
     DatePicker
    -0.06
    ्यव
    -0.06
     adr
    -0.06
    POSITIVE LOGITS
    _operand
    0.07
     Daytona
    0.06
    Ă
    0.06
    scious
    0.06
    ORD
    0.06
    _ENABLED
    0.06
     OUR
    0.06
     Maple
    0.06
    .Trans
    0.06
     Virgin
    0.06
    Act Density 0.002%

    No Known Activations