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

    Neuronpedia

    INDEX
    Explanations

    DR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stunt
    -0.06
     impacting
    -0.06
     influencing
    -0.06
    arefa
    -0.06
    easy
    -0.06
    Coding
    -0.06
    Blo
    -0.06
    alarında
    -0.06
    ůst
    -0.06
     Picture
    -0.06
    POSITIVE LOGITS
     singular
    0.07
    qrt
    0.06
     thể
    0.06
    rary
    0.06
     Sloan
    0.06
     总
    0.06
    /portfolio
    0.06
    abl
    0.06
    ":[{↵
    0.06
    pr
    0.06
    Act Density 0.005%

    No Known Activations