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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash

    This neuron detects LaTeX package names (the tokens inside \usepackage{…} declarations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     object
    -0.06
     blockers
    -0.06
    /report
    -0.06
     Therm
    -0.06
    (se
    -0.06
     Misc
    -0.06
     homo
    -0.06
     Proposal
    -0.06
     Earl
    -0.06
     individ
    -0.06
    POSITIVE LOGITS
    arton
    0.08
    ush
    0.07
    い
    0.07
    HK
    0.06
    /manual
    0.06
    uffy
    0.06
    leta
    0.06
     QtAws
    0.06
     Mozilla
    0.06
    软雅黑
    0.06
    Act Density 0.001%

    No Known Activations