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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or hypothetical scenarios

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

    Preceding "return," "provide," "go," etc., after "would"

    np_acts-logits-general · gemini-2.0-flash

    would followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Eure
    -0.42
    ("."
    -0.40
    "",
    -0.37
    (=)
    -0.36
     [*]
    -0.35
    [-]
    -0.34
    ('.')
    -0.34
     isSet
    -0.33
    (">>
    -0.32
     Jail
    -0.31
    POSITIVE LOGITS
    would
    0.90
     WOULD
    0.88
     would
    0.88
    Would
    0.87
     Would
    0.85
    JvmStatic
    0.72
    出版年
    0.67
     Gould
    0.66
    OGND
    0.65
    ########.
    0.61
    Act Density 0.189%

    No Known Activations