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

    Neuronpedia

    INDEX
    Explanations

    script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    增长
    -0.07
     theatrical
    -0.07
    追
    -0.07
    анием
    -0.06
    	re
    -0.06
    ア
    -0.06
    Theta
    -0.06
    {↵↵↵
    -0.06
    ean
    -0.06
    OLLOW
    -0.06
    POSITIVE LOGITS
    _IMAGES
    0.07
    bolt
    0.06
     елем
    0.06
     Lastly
    0.06
     Yates
    0.06
     Faith
    0.06
     RaycastHit
    0.06
     issuing
    0.06
    imals
    0.05
    uştur
    0.05
    Act Density 0.001%

    No Known Activations