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

    Neuronpedia

    INDEX
    Explanations

    general inspection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    voir
    0.55
     B
    0.50
     Rev
    0.46
     Op
    0.46
     Nevis
    0.46
     Ir
    0.45
    B
    0.44
     Ко
    0.44
    ↵
    0.44
     Pop
    0.42
    POSITIVE LOGITS
    ㅄ
    0.47
    shmi
    0.47
    احمد
    0.46
    <unused722>
    0.46
    avourable
    0.46
     lakini
    0.46
     다양한
    0.45
     spacerItem
    0.45
    ುಂಬ
    0.45
    ଁ
    0.45
    Act Density 0.004%

    No Known Activations