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

    Neuronpedia

    INDEX
    Explanations

    exercises and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Outline
    0.40
    Paying
    0.40
     paying
    0.39
     Clutch
    0.39
    Outline
    0.39
     Comedy
    0.39
     Accuracy
    0.38
    优先级
    0.38
     priority
    0.38
     Priority
    0.38
    POSITIVE LOGITS
    она
    0.48
    vants
    0.45
     exercícios
    0.44
     exercices
    0.44
     lineColorSpace
    0.42
     procé
    0.42
    ন্তা
    0.42
    ូន
    0.40
     ressources
    0.40
     exercice
    0.40
    Act Density 0.000%

    No Known Activations