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

    Neuronpedia

    INDEX
    Explanations

    book descriptions

    np_max-act · gemini-2.0-flash

    The neuron detects metadata labels and structural markers in book listings (e.g. “Book Description,” “Condition:,” inventory or ISBN numbers, and related header tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     рад
    -0.07
    =img
    -0.07
    .AppendText
    -0.07
    ($"{
    -0.07
    Sampling
    -0.07
    =zeros
    -0.07
    =rand
    -0.07
    chimp
    -0.07
    _"+
    -0.06
    _IGNORE
    -0.06
    POSITIVE LOGITS
    -bre
    0.06
    ้าว
    0.06
    187
    0.06
    甲
    0.06
    -depth
    0.06
    ournaments
    0.06
    osex
    0.06
     Lunch
    0.06
    руп
    0.06
    emme
    0.06
    Act Density 0.001%

    No Known Activations