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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    だが
    -0.08
     Thomas
    -0.07
     цель
    -0.07
    .dc
    -0.06
     mediated
    -0.06
    �t
    -0.06
    ∨
    -0.06
    ="--
    -0.06
     Reeves
    -0.06
    CppMethodInitialized
    -0.06
    POSITIVE LOGITS
    Whitespace
    0.07
    لي
    0.07
     Conditioning
    0.06
    ,L
    0.06
    ,J
    0.06
    isine
    0.06
    _precision
    0.06
    ('_
    0.06
    (sem
    0.06
     маль
    0.06
    Act Density 0.001%

    No Known Activations