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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron detects uppercase initialisms or acronyms (multi-letter all-caps abbreviations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Northwestern
    -0.07
     =================================
    -0.07
     shifted
    -0.07
     Cooke
    -0.07
     Fra
    -0.07
     //////
    -0.06
     Covenant
    -0.06
     commas
    -0.06
     attacked
    -0.06
     prolonged
    -0.06
    POSITIVE LOGITS
    prm
    0.06
    ��
    0.06
    )p
    0.06
    ýš
    0.06
     önemlidir
    0.06
     oxide
    0.06
     politic
    0.06
    .IsAny
    0.06
    SuppressLint
    0.06
     ​​
    0.06
    Act Density 0.018%

    No Known Activations