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

    Neuronpedia

    INDEX
    Explanations

    specific follow-ups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.73
    zellen
    0.70
    ischen
    0.69
     Tarifleri
    0.67
    Cell
    0.66
    Gon
    0.65
    िकांनी
    0.64
    Phi
    0.64
     पीएच
    0.64
    Bull
    0.64
    POSITIVE LOGITS
     paralel
    0.75
     নিঃসন্দে
    0.72
     sparring
    0.70
     неба
    0.70
     AM
    0.69
    рее
    0.67
     علاقه
    0.67
     বিদেশী
    0.65
     подразде
    0.65
     dapp
    0.65
    Act Density 0.000%

    No Known Activations