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

    Neuronpedia

    INDEX
    Explanations

    C++ code

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric literals (e.g. integer or floating-point constants) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     查询
    -0.06
    {};↵
    -0.06
    وتر
    -0.06
    iform
    -0.06
    ylinder
    -0.06
    ocities
    -0.06
     serene
    -0.06
    (phi
    -0.06
    IMG
    -0.06
    """)↵
    -0.06
    POSITIVE LOGITS
    POSITION
    0.07
     blij
    0.07
    .decorators
    0.06
     somehow
    0.06
     —
    0.06
     поперед
    0.06
    .localtime
    0.06
    .Annotation
    0.06
    损
    0.06
     üretim
    0.06
    Act Density 0.046%

    No Known Activations