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

    Neuronpedia

    INDEX
    Explanations

    assignments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    `=` followed by a LoggerFactory method

    np_acts-logits-general · gemini-2.0-flash

    LoggerFactory, Executors, new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     E
    -0.53
    eip
    -0.52
    :+:
    -0.49
    ↵↵
    -0.49
    itattu
    -0.48
    E
    -0.48
    ↵
    -0.48
    .
    -0.46
     길
    -0.45
    ,
    -0.45
    POSITIVE LOGITS
     houſe
    0.95
     purpoſe
    0.89
     Monfieur
    0.88
    ſelves
    0.84
     Majefty
    0.84
     ―――――
    0.83
     Efq
    0.83
     pleaſure
    0.83
     useNavigate
    0.82
     ſta
    0.81
    Act Density 0.098%

    No Known Activations