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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Local
    -0.08
     loan
    -0.07
     Wich
    -0.07
     xc
    -0.07
    iks
    -0.07
    leniyor
    -0.07
    τί
    -0.06
    \e
    -0.06
     weapon
    -0.06
    ΙΚ
    -0.06
    POSITIVE LOGITS
    -create
    0.07
    Anime
    0.06
    .require
    0.06
    ############################
    0.06
     imkân
    0.06
    มนตร
    0.06
     نش
    0.06
    odate
    0.06
    �
    0.06
     �
    0.06
    Act Density 0.019%

    No Known Activations