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
     이러
    -0.07
     fontWeight
    -0.07
    στό
    -0.07
     jt
    -0.06
    ّا
    -0.06
     mA
    -0.06
     standpoint
    -0.06
     постро
    -0.06
    шими
    -0.06
    “.
    -0.06
    POSITIVE LOGITS
     ヾ
    0.07
    иль
    0.06
    Conversation
    0.06
    -git
    0.06
    ・━
    0.06
     Влади
    0.06
     psychedelic
    0.06
     MVP
    0.06
     mare
    0.06
     quits
    0.06
    Act Density 0.015%

    No Known Activations