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

    Neuronpedia

    INDEX
    Explanations

    entry

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the token “entry” when it’s used as a structural field or tag name in code or data (e.g. JSON/ XML “entry” objects).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Paul
    -0.07
    Paul
    -0.07
    484
    -0.07
    Hum
    -0.07
    .raise
    -0.07
     Sage
    -0.06
     luc
    -0.06
     Qualität
    -0.06
    777
    -0.06
     personals
    -0.06
    POSITIVE LOGITS
     entry
    0.13
     Entry
    0.11
    ENTRY
    0.10
     entries
    0.10
    entries
    0.10
    (entries
    0.10
    entry
    0.09
     ENTRY
    0.09
    	entry
    0.09
    (entry
    0.09
    Act Density 0.015%

    No Known Activations