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

    Neuronpedia

    INDEX
    Explanations

    Software testing

    np_max-act · gemini-2.0-flash

    The neuron specializes in detecting programming‐language identifiers and technical code tokens (e.g. class, method, and package names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    Buy
    -0.07
     GetAll
    -0.06
     View
    -0.06
    ことを
    -0.06
     consciously
    -0.06
    ама
    -0.06
    ्यम
    -0.06
    系列
    -0.06
     نتیجه
    -0.06
    POSITIVE LOGITS
    hashCode
    0.07
     friendship
    0.07
    grey
    0.07
     ilan
    0.06
     Biblical
    0.06
     Gree
    0.06
     phil
    0.06
    hh
    0.06
     dětí
    0.06
     Rach
    0.06
    Act Density 0.016%

    No Known Activations