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

    Neuronpedia

    INDEX
    Explanations

    interval or time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ements
    -0.08
    али
    -0.07
    .*
    -0.06
    اما
    -0.06
    ینک
    -0.06
    lamp
    -0.06
     ά
    -0.06
    тар
    -0.06
    進行
    -0.06
    thy
    -0.06
    POSITIVE LOGITS
    âh
    0.07
    .fe
    0.07
     bab
    0.07
    0.06
     delays
    0.06
    	padding
    0.06
     mucho
    0.06
    noinspection
    0.06
    œ
    0.06
     Mono
    0.06
    Act Density 0.044%

    No Known Activations