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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on personal names (proper nouns referring to people).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     quant
    -0.06
    alach
    -0.06
    シャ
    -0.06
     Pru
    -0.06
    арь
    -0.06
     LICENSE
    -0.06
    	TR
    -0.06
     Rust
    -0.05
    nor
    -0.05
    裡
    -0.05
    POSITIVE LOGITS
    働
    0.07
    怒
    0.07
     cé
    0.07
     understood
    0.06
    (other
    0.06
    -json
    0.06
    であった
    0.06
     ـ
    0.06
     whirl
    0.06
     Www
    0.06
    Act Density 0.129%

    No Known Activations