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

    Neuronpedia

    INDEX
    Explanations

    Code/data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rules
    -0.07
    -google
    -0.07
    .Task
    -0.07
     Partition
    -0.07
    ę
    -0.07
    Terr
    -0.06
     TOTAL
    -0.06
     gravitational
    -0.06
     negatives
    -0.06
     кому
    -0.06
    POSITIVE LOGITS
    зя
    0.06
     nitelik
    0.06
     wallpaper
    0.06
    strict
    0.06
    Classifier
    0.06
    产生
    0.06
    тоф
    0.06
     numéro
    0.06
    итом
    0.06
    işim
    0.05
    Act Density 0.033%

    No Known Activations