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

    Neuronpedia

    INDEX
    Explanations

    brand names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    رو
    0.40
     kabel
    0.40
     вопроса
    0.40
    beda
    0.39
     hoher
    0.39
     pohon
    0.39
    iotic
    0.39
     luft
    0.38
    robi
    0.38
     automatisch
    0.38
    POSITIVE LOGITS
    ™
    0.87
    ™,
    0.83
    ™.
    0.75
    ℠
    0.66
    ®
    0.62
     ™
    0.62
     initiative
    0.59
     Initiative
    0.58
     Podcast
    0.57
    ®,
    0.57
    Act Density 0.042%

    No Known Activations