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
     falando
    -0.08
     మాట్లాడుతూ
    -0.08
    awia
    -0.07
    }\"
    -0.07
     poverty
    -0.07
     বক্ত
    -0.07
     cham
    -0.07
    Discuss
    -0.07
     princípios
    -0.07
     perfeitamente
    -0.07
    POSITIVE LOGITS
    クリック
    0.10
     아래
    0.09
     클릭
    0.09
    -click
    0.09
    ください
    0.09
     beware
    0.09
     klicken
    0.09
    下さい
    0.09
     点击
    0.09
     hieronder
    0.08
    Act Density 0.047%

    No Known Activations