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

    Neuronpedia

    INDEX
    Explanations

    occurrences of underscores followed by code-related identifiers

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

    python dunder methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.69
     AssemblyCompany
    -0.68
     estekak
    -0.65
    afficheront
    -0.62
     مشين
    -0.62
     '\\;'
    -0.58
    tvguidetime
    -0.57
    цездатний
    -0.55
     indisponible
    -0.54
    rungsseite
    -0.53
    POSITIVE LOGITS
    __
    0.87
    __);
    0.53
    __))
    0.49
    leger
    0.47
    __'
    0.44
     nữa
    0.42
    WebControls
    0.42
     __
    0.42
    __]
    0.41
    ||}
    0.40
    Act Density 0.011%

    No Known Activations