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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ename
    -0.07
    DST
    -0.07
    aru
    -0.06
     SER
    -0.06
    ред
    -0.06
     interfere
    -0.06
    iola
    -0.06
     wi
    -0.06
    idd
    -0.06
    aldi
    -0.06
    POSITIVE LOGITS
     sockfd
    0.07
    �
    0.07
    objectManager
    0.07
     كور
    0.06
     гот
    0.06
    →→
    0.06
    instead
    0.06
     направ
    0.06
     обла
    0.06
     souvis
    0.06
    Act Density 0.000%

    No Known Activations