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

    Neuronpedia

    INDEX
    Explanations

    Pickled foods

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of pickles or pickling (e.g., words like “pickle,” “pickled,” “pickling”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _content
    -0.07
     BMI
    -0.07
     ~/
    -0.07
     dataSize
    -0.07
    .Percent
    -0.07
     TCHAR
    -0.07
     призна
    -0.07
     sleeping
    -0.06
    يمة
    -0.06
     Tests
    -0.06
    POSITIVE LOGITS
    -controlled
    0.07
     fiery
    0.06
    ây
    0.06
    fet
    0.06
     amort
    0.06
     tropical
    0.06
    olv
    0.06
    .allocate
    0.06
    .Lib
    0.06
    .setEnabled
    0.06
    Act Density 0.013%

    No Known Activations