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

    Neuronpedia

    INDEX
    Explanations

    countries of origin

    np_max-act · gemini-2.0-flash

    The neuron detects country-of-origin phrases (e.g., “Made in Italy,” “Made in Japan”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Damage
    -0.07
     ribs
    -0.06
     کمتر
    -0.06
    APA
    -0.06
     Cable
    -0.06
    hasMany
    -0.06
    ูงส
    -0.06
     Aber
    -0.06
    _PWM
    -0.06
     Erect
    -0.06
    POSITIVE LOGITS
     conn
    0.07
     singleton
    0.06
     penal
    0.06
     Chow
    0.06
     welcome
    0.06
     duel
    0.06
    esel
    0.06
     exem
    0.06
     beautiful
    0.06
     đức
    0.06
    Act Density 0.014%

    No Known Activations