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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Titles
    -0.07
    �
    -0.07
    Filters
    -0.07
     blindness
    -0.06
     TRACK
    -0.06
     gpointer
    -0.06
    (ip
    -0.06
     kaz
    -0.06
    Rank
    -0.06
     Beach
    -0.06
    POSITIVE LOGITS
    _ERRORS
    0.07
    liği
    0.07
     indem
    0.07
     půj
    0.06
    Что
    0.06
    .current
    0.06
    .parentElement
    0.06
    ieron
    0.06
    (selected
    0.06
    シェ
    0.06
    Act Density 0.013%

    No Known Activations