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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     achievable
    -0.07
    当之无
    -0.07
    פועל
    -0.07
     wages
    -0.07
    _mA
    -0.07
     chickens
    -0.07
     ),
    -0.07
    ))*(
    -0.06
     wound
    -0.06
    回头
    -0.06
    POSITIVE LOGITS
    سلام
    0.07
     Neck
    0.07
     nov
    0.07
     outing
    0.07
     Cap
    0.07
    뺃
    0.06
     Buy
    0.06
     chants
    0.06
     errorCode
    0.06
     hostility
    0.06
    Act Density 0.130%

    No Known Activations