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

    Neuronpedia

    INDEX
    Explanations

    code and algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    glich
    -0.08
    ylül
    -0.07
    .optim
    -0.07
     instala
    -0.07
    świ
    -0.07
    });↵↵//
    -0.07
     설치
    -0.07
     сум
    -0.07
     baile
    -0.07
     synergy
    -0.07
    POSITIVE LOGITS
     redistributed
    0.11
     terug
    0.10
     tilbage
    0.10
     redistribute
    0.09
     recycled
    0.09
     recyclable
    0.09
     tillbaka
    0.09
     recycle
    0.09
     обратно
    0.09
    กลับ
    0.09
    Act Density 0.006%

    No Known Activations