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

    Neuronpedia

    INDEX
    Explanations

    ID

    np_max-act · gemini-2.0-flash

    The neuron fires on the JSON metadata keys and values that denote CVE identifiers and related vulnerability‐report fields (e.g. “CVE‐YYYY‐NNNN,” “ID,” “data_format,” “references,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .bucket
    -0.07
     �
    -0.07
    setOnClickListener
    -0.07
     garbage
    -0.07
    แ
    -0.07
     حف
    -0.07
     ure
    -0.06
     згад
    -0.06
    सत
    -0.06
     kvp
    -0.06
    POSITIVE LOGITS
    owo
    0.07
     notorious
    0.07
    aways
    0.06
    -fashioned
    0.06
    lle
    0.06
     forb
    0.06
    atural
    0.06
    fty
    0.06
    ��
    0.06
    owie
    0.06
    Act Density 0.008%

    No Known Activations