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

    Neuronpedia

    INDEX
    Explanations

    climate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    披
    -0.07
     clad
    -0.07
    tract
    -0.07
     ya
    -0.06
     Dund
    -0.06
     unle
    -0.06
    十四
    -0.06
    strength
    -0.06
     доб
    -0.06
     bun
    -0.06
    POSITIVE LOGITS
     PF
    0.07
    쇤
    0.07
    اجتماع
    0.06
    groupBy
    0.06
    奋斗目标
    0.06
    Emitter
    0.06
    减速
    0.06
    🕟
    0.06
     INF
    0.06
     societal
    0.06
    Act Density 0.018%

    No Known Activations