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

    Neuronpedia

    INDEX
    Explanations

    Method

    np_max-act · gemini-2.0-flash

    The neuron fires on reflection‐API calls (e.g. GetMethod/GetProperty, MakeGenericMethod, MethodInfo.Invoke) indicating dynamic invocation via reflection.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _strdup
    -0.07
    lap
    -0.06
     kháng
    -0.06
    ÜRK
    -0.06
    _out
    -0.06
     dcc
    -0.06
    :].
    -0.06
     Bishop
    -0.06
    yang
    -0.06
    ALL
    -0.06
    POSITIVE LOGITS
     jars
    0.06
     releg
    0.06
     Allowed
    0.06
     bois
    0.06
    datum
    0.06
     includ
    0.06
     dut
    0.06
     punt
    0.06
     segundos
    0.06
     suffered
    0.06
    Act Density 0.009%

    No Known Activations