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

    Neuronpedia

    INDEX
    Explanations

    prerequisite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     directive
    -0.08
     thinking
    -0.07
     Lena
    -0.07
     sınır
    -0.06
    าด
    -0.06
    Transmission
    -0.06
    علام
    -0.06
     still
    -0.06
     intersection
    -0.06
     acts
    -0.06
    POSITIVE LOGITS
     prerequisite
    0.13
     prerequisites
    0.13
    erequisites
    0.11
     requisite
    0.08
    erequisite
    0.08
    tolua
    0.08
    quisites
    0.08
    quisite
    0.07
    ++)↵
    0.07
     Prev
    0.07
    Act Density 0.006%

    No Known Activations