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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lista
    -0.07
     YT
    -0.07
     verilm
    -0.06
     Wellness
    -0.06
    liness
    -0.06
     (){↵
    -0.06
     Анд
    -0.06
     víc
    -0.06
     Pixar
    -0.06
     نیر
    -0.06
    POSITIVE LOGITS
     nib
    0.07
    ession
    0.06
     herbal
    0.06
     Pavel
    0.06
     noct
    0.06
    PECIAL
    0.06
    (paths
    0.06
    //↵↵
    0.06
     IconData
    0.06
    agate
    0.06
    Act Density 0.000%

    No Known Activations