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

    Neuronpedia

    INDEX
    Explanations

    concept followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     There
    0.44
     shipping
    0.44
     This
    0.43
     different
    0.43
     Bicycle
    0.42
     It
    0.42
     treat
    0.41
     it
    0.41
     transportation
    0.41
     version
    0.41
    POSITIVE LOGITS
    ♌
    0.48
    ฟ้า
    0.46
     destacó
    0.46
     తొలి
    0.45
    <unused601>
    0.45
     değiş
    0.45
     erstmals
    0.44
     octubre
    0.44
     पढ़े
    0.44
     símbolos
    0.44
    Act Density 0.005%

    No Known Activations