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

    Neuronpedia

    INDEX
    Explanations

    model starting with Okay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mojo
    0.41
     Lobster
    0.40
     the
    0.39
    Cliff
    0.39
    lni
    0.39
    сто
    0.39
     собой
    0.39
    จุ
    0.38
    عت
    0.38
     коло
    0.38
    POSITIVE LOGITS
     forcément
    0.46
     compliqué
    0.44
     അവളുടെ
    0.44
     pourrait
    0.43
    écut
    0.43
    څ
    0.42
     définition
    0.42
    aminen
    0.41
    udrait
    0.41
    툼
    0.40
    Act Density 0.002%

    No Known Activations