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

    Neuronpedia

    INDEX
    Explanations

    Java code/errors

    np_max-act · gemini-2.0-flash

    The neuron activates on the numeric line-number annotations in code stack traces (e.g. the “filename.java:123” parts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    turned
    -0.08
     zwe
    -0.07
    _finder
    -0.07
    +j
    -0.06
    624
    -0.06
    ları
    -0.06
    igt
    -0.06
    binary
    -0.06
    еви
    -0.06
    Pix
    -0.06
    POSITIVE LOGITS
    .DropDown
    0.07
     Declarations
    0.07
     AssemblyCopyright
    0.06
     _:
    0.06
    ób
    0.06
     Rudd
    0.06
     Зап
    0.06
     �
    0.06
     chemotherapy
    0.06
    (completion
    0.06
    Act Density 0.004%

    No Known Activations