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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     urine
    -0.06
     Pivot
    -0.06
    Enumerator
    -0.06
     Surgery
    -0.06
    ы
    -0.06
    omes
    -0.06
     networks
    -0.06
     elastic
    -0.06
     Kawasaki
    -0.06
    .memory
    -0.06
    POSITIVE LOGITS
    !,↵
    0.07
    ()");↵
    0.07
     destroying
    0.06
    iềm
    0.06
     banc
    0.06
     dài
    0.06
    站在
    0.06
    _ast
    0.06
     З
    0.06
     lyr
    0.06
    Act Density 0.004%

    No Known Activations