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

    Neuronpedia

    INDEX
    Explanations

    caramel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	
↵
    -0.07
     legs
    -0.06
     });↵
    -0.06
     教
    -0.06
     Winchester
    -0.06
     رم
    -0.06
    Now
    -0.06
    犬
    -0.06
     فق
    -0.06
     representatives
    -0.06
    POSITIVE LOGITS
     caramel
    0.16
    aramel
    0.13
     Carm
    0.08
    ponsors
    0.07
    (CancellationToken
    0.07
    ormal
    0.07
     community
    0.07
    okin
    0.07
    ğe
    0.07
    omes
    0.07
    Act Density 0.001%

    No Known Activations