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

    Neuronpedia

    INDEX
    Explanations

    scopic

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on subwords ending in “scopic” (as in “arthroscopic,” “endoscopic,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Hav
    -0.07
    Put
    -0.07
     fire
    -0.07
     pessoa
    -0.06
    Str
    -0.06
     prejudice
    -0.06
    地
    -0.06
    /weather
    -0.06
     quantities
    -0.06
     task
    -0.06
    POSITIVE LOGITS
     अगर
    0.07
     defaultValue
    0.07
     Cisco
    0.07
    ason
    0.07
    .Design
    0.06
    .backward
    0.06
     oracle
    0.06
     чис
    0.06
     carrots
    0.06
    ©©
    0.06
    Act Density 0.001%

    No Known Activations