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

    Neuronpedia

    INDEX
    Explanations

    option

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     رفت
    -0.08
     Surface
    -0.07
    _USER
    -0.07
     users
    -0.07
     vector
    -0.07
     piece
    -0.07
     audience
    -0.07
    _bus
    -0.06
    tank
    -0.06
    _LESS
    -0.06
    POSITIVE LOGITS
     option
    0.08
    =explode
    0.07
    Option
    0.06
     widening
    0.06
     tablespoons
    0.06
     Option
    0.06
     possibilities
    0.06
     Bordeaux
    0.06
     progressive
    0.06
    :boolean
    0.06
    Act Density 0.021%

    No Known Activations