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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Phone
    -0.07
     민주
    -0.07
    Phones
    -0.06
     zinc
    -0.06
     USERS
    -0.06
     دشمن
    -0.06
    coat
    -0.06
     Rent
    -0.06
    Indexed
    -0.06
    specified
    -0.06
    POSITIVE LOGITS
    lparr
    0.07
    žil
    0.06
     nemoh
    0.06
     bordel
    0.06
    /sbin
    0.06
     agon
    0.06
     plus
    0.06
     Added
    0.06
     Cran
    0.06
    (qu
    0.06
    Act Density 0.053%

    No Known Activations