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

    Neuronpedia

    INDEX
    Explanations

    language learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ageing
    -0.07
     twisted
    -0.07
     알고
    -0.07
    _skill
    -0.07
    Where
    -0.07
    ply
    -0.06
    atty
    -0.06
    _________________↵↵
    -0.06
    .When
    -0.06
    Factor
    -0.06
    POSITIVE LOGITS
     bark
    0.06
    _decoder
    0.06
    _simulation
    0.06
    cks
    0.05
     문의
    0.05
    Called
    0.05
    ailure
    0.05
     perfected
    0.05
    QUOTE
    0.05
    ACK
    0.05
    Act Density 0.076%

    No Known Activations