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

    Neuronpedia

    INDEX
    Explanations

    both sides of equation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enjeux
    0.45
     temporadas
    0.44
     gastronomic
    0.43
     zhī
    0.43
     Gründung
    0.42
     gestão
    0.42
     histórias
    0.42
     alberga
    0.41
     communautés
    0.41
     vik
    0.40
    POSITIVE LOGITS
     Move
    0.40
    Equations
    0.40
     Lock
    0.40
    方程
    0.39
     ecuaciones
    0.38
    Removing
    0.38
     Fudge
    0.38
    消除
    0.37
    衡
    0.37
     equations
    0.37
    Act Density 0.065%

    No Known Activations