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

    Neuronpedia

    INDEX
    Explanations

    Numerical statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .emptyList
    -0.07
    إدارة
    -0.07
     addictive
    -0.07
    .Magenta
    -0.07
    ,axis
    -0.07
     trenches
    -0.07
    𝘌
    -0.07
     através
    -0.07
     tempting
    -0.07
    ることができます
    -0.07
    POSITIVE LOGITS
    (--
    0.07
    在床上
    0.07
     Kelly
    0.06
    richt
    0.06
    萊
    0.06
     grad
    0.06
    תמ
    0.06
     screenWidth
    0.06
     fluores
    0.06
     Sk
    0.06
    Act Density 0.548%

    No Known Activations