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

    Neuronpedia

    INDEX
    Explanations

    Tiger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rt
    -0.07
    623
    -0.07
     zahrani
    -0.06
     QMessageBox
    -0.06
     onto
    -0.06
    来
    -0.06
     ayant
    -0.06
     nearly
    -0.06
     Walt
    -0.06
     emitting
    -0.06
    POSITIVE LOGITS
     Tiger
    0.18
     tiger
    0.15
    iger
    0.13
    igers
    0.09
     Panther
    0.09
     Tigers
    0.09
    虎
    0.08
     Jaguars
    0.08
     Tig
    0.07
     Creature
    0.07
    Act Density 0.006%

    No Known Activations