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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    notice
    -0.07
    96
    -0.07
     anger
    -0.06
    "?
    -0.06
    	dialog
    -0.06
    20
    -0.06
    Aw
    -0.06
     seconds
    -0.06
    neg
    -0.06
    ]=='
    -0.06
    POSITIVE LOGITS
     řešení
    0.07
     subparagraph
    0.06
    -effect
    0.06
     fidelity
    0.06
    ματος
    0.06
    xico
    0.06
    eking
    0.06
    pcion
    0.06
    ví
    0.06
    ImageContext
    0.06
    Act Density 0.016%

    No Known Activations