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

    Neuronpedia

    INDEX
    Explanations

    excerpts

    np_max-act · gemini-2.0-flash

    This neuron detects file‐system path or filename tokens (e.g. header includes and “/var/tmp/…” style paths).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ()"↵
    -0.07
    自動
    -0.07
     디자인
    -0.06
    Lock
    -0.06
    )}"↵
    -0.06
     Traditional
    -0.06
     Broadcast
    -0.06
     GLOBAL
    -0.06
     chast
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     dernier
    0.07
    )dealloc
    0.06
     binge
    0.06
    inta
    0.06
     soo
    0.06
     mois
    0.06
    OE
    0.06
    赛
    0.06
     sore
    0.06
     både
    0.06
    Act Density 0.246%

    No Known Activations