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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the phrase “check if” (especially the “check” followed by “if”) in questions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Fiscal
    -0.08
    .Rad
    -0.08
    massage
    -0.07
    .merge
    -0.07
     آسی
    -0.07
    .Log
    -0.07
    nil
    -0.06
     oppressed
    -0.06
    ngör
    -0.06
    Por
    -0.06
    POSITIVE LOGITS
    commons
    0.07
    Longrightarrow
    0.06
    ,String
    0.06
    published
    0.06
    сут
    0.06
     اروپ
    0.06
    .grid
    0.06
    .Alignment
    0.06
    ///↵
    0.06
    />";↵
    0.05
    Act Density 0.013%

    No Known Activations