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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    This neuron activates on class‐declaration inheritance/implementation clauses—i.e. keywords like “implements,” “extends,” and access specifiers (“public”/“private”) in class definitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    "])↵↵
    -0.07
     Orlando
    -0.06
     packages
    -0.06
     δύο
    -0.06
    "↵↵↵↵
    -0.06
     advocated
    -0.06
    �述
    -0.06
     číslo
    -0.06
     Orleans
    -0.06
     alleging
    -0.06
    POSITIVE LOGITS
    _generator
    0.07
    Meteor
    0.07
    ounce
    0.07
     Organ
    0.07
     Sew
    0.06
    Clin
    0.06
    -wheel
    0.06
    `),↵
    0.06
    0.06
     sare
    0.06
    Act Density 0.003%

    No Known Activations