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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ADIO
    -0.06
     rover
    -0.06
    ocalyptic
    -0.06
     İŞ
    -0.06
    icl
    -0.06
     آل
    -0.06
     publik
    -0.06
     Letter
    -0.06
    elerini
    -0.06
     Bahrain
    -0.06
    POSITIVE LOGITS
    ，在
    0.08
    >'
↵
    0.07
    =zeros
    0.07
     Adult
    0.07
    μα
    0.06
     gating
    0.06
     ttl
    0.06
    َم
    0.06
    thickness
    0.06
    私の
    0.06
    Act Density 0.002%

    No Known Activations