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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Employee
    -0.07
    -num
    -0.07
    IGENCE
    -0.06
    Rose
    -0.06
     Log
    -0.06
     Know
    -0.06
    网点
    -0.06
    Grant
    -0.06
    right
    -0.06
    ;(
    -0.06
    POSITIVE LOGITS
    .Al
    0.07
    apsulation
    0.07
    ϐ
    0.07
     bardzo
    0.07
     Brun
    0.07
     utilis
    0.07
    laş
    0.07
    À
    0.07
    .getDefault
    0.06
     cvs
    0.06
    Act Density 0.074%

    No Known Activations