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

    Neuronpedia

    INDEX
    Explanations

    toy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Path
    -0.08
     kancel
    -0.08
    idence
    -0.07
     commence
    -0.07
     graduate
    -0.07
     doctoral
    -0.07
     Quit
    -0.07
     základě
    -0.06
     února
    -0.06
    Merit
    -0.06
    POSITIVE LOGITS
     Toys
    0.10
     toys
    0.09
     toy
    0.09
     Toy
    0.09
    rot
    0.07
    Toy
    0.07
     Jared
    0.07
    拥
    0.07
    otyp
    0.06
    품
    0.06
    Act Density 0.011%

    No Known Activations