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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سبک
    -0.06
    cript
    -0.06
     Followers
    -0.06
     страны
    -0.06
    ريك
    -0.06
     spectro
    -0.06
    edef
    -0.06
    Authority
    -0.06
    571
    -0.06
    (stmt
    -0.06
    POSITIVE LOGITS
     diy
    0.07
     HI
    0.07
    mania
    0.07
     newState
    0.06
    ilebilir
    0.06
    uction
    0.06
     onion
    0.06
     }↵
    0.06
    offset
    0.06
     koc
    0.06
    Act Density 0.002%

    No Known Activations