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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interessados
    -0.08
    _BUSY
    -0.08
     supposedly
    -0.08
     merely
    -0.07
     избор
    -0.07
    Busy
    -0.07
     Interested
    -0.07
    Ale
    -0.07
    ашт
    -0.07
     zainteres
    -0.07
    POSITIVE LOGITS
    obil
    0.08
     pinaka
    0.08
    large
    0.08
    omit
    0.08
     sâu
    0.08
     comprehensive
    0.08
     сильно
    0.08
     साम
    0.07
     maje
    0.07
    macro
    0.07
    Act Density 0.023%

    No Known Activations