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

    Neuronpedia

    INDEX
    Explanations

    filler list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gratuita
    0.57
     painless
    0.57
     cashless
    0.55
     fruitless
    0.52
     firearm
    0.52
     wastage
    0.51
     dismin
    0.50
     civilized
    0.50
     सब्सिडी
    0.50
     desee
    0.50
    POSITIVE LOGITS
    了一些
    0.59
    ventures
    0.55
    系の
    0.55
    őbb
    0.55
     kteří
    0.54
    Chemistry
    0.54
    重要
    0.53
    Molecular
    0.53
    rones
    0.52
    rios
    0.52
    Act Density 0.497%

    No Known Activations