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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to leaks or leaking

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

    leak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Modus
    -0.52
     Bowman
    -0.51
    CommandType
    -0.50
    ptonshire
    -0.49
     Vanden
    -0.47
    ngrx
    -0.47
     Carlson
    -0.47
     Gros
    -0.47
     emphat
    -0.47
     Thomson
    -0.46
    POSITIVE LOGITS
     leak
    2.11
     Leak
    1.93
    leak
    1.88
    Leak
    1.84
     leaks
    1.82
     Leaks
    1.58
     leaking
    1.54
     leakage
    1.53
     Leakage
    1.43
     leaked
    1.40
    Act Density 0.008%

    No Known Activations