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

    Neuronpedia

    INDEX
    Explanations

    C++ code configuration

    np_max-act · gemini-2.0-flash

    The neuron is triggered by C/C++ preprocessor macro names (identifiers in all-caps with underscores).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    reat
    -0.06
     Slovakia
    -0.06
    ocz
    -0.06
     Griffin
    -0.06
     newspaper
    -0.06
    .login
    -0.06
     CLIIIK
    -0.06
     Slovak
    -0.06
    qw
    -0.06
    евые
    -0.06
    POSITIVE LOGITS
    iah
    0.07
    (IO
    0.07
     共
    0.07
    (Activity
    0.06
    celed
    0.06
     midd
    0.06
    ์↵↵
    0.06
     PS
    0.06
    dl
    0.06
    .trip
    0.06
    Act Density 0.011%

    No Known Activations