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

    Neuronpedia

    INDEX
    Explanations

    waste

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unst
    -0.08
     unstable
    -0.08
     pul
    -0.08
     verse
    -0.08
     गीत
    -0.08
     বাহ
    -0.07
     crooked
    -0.07
     ಹಾಡ
    -0.07
     trai
    -0.07
    wiki
    -0.07
    POSITIVE LOGITS
    弃
    0.10
     отход
    0.09
     pharmaceutical
    0.09
     처리
    0.08
     발생
    0.08
     landfill
    0.08
     tonnes
    0.08
    ымыз
    0.08
     toneladas
    0.08
    ządz
    0.07
    Act Density 0.011%

    No Known Activations