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

    Neuronpedia

    INDEX
    Explanations

    protect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     txn
    -0.06
     words
    -0.06
    Global
    -0.06
    _phase
    -0.06
    .Doc
    -0.06
     Assassin
    -0.06
    ↵     ↵
    -0.06
     motivations
    -0.05
     Hun
    -0.05
     Global
    -0.05
    POSITIVE LOGITS
     بالأ
    0.07
    alary
    0.07
     Czech
    0.07
    -kit
    0.06
    (domain
    0.06
    �
    0.06
    �
    0.06
     harb
    0.06
    τογραφ
    0.06
     клет
    0.06
    Act Density 0.049%

    No Known Activations