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

    Neuronpedia

    INDEX
    Explanations

    built, voice, data, Goal, networking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hurricane
    0.40
     evaded
    0.39
    featured
    0.39
    ೬
    0.38
    یرے
    0.36
    ڑوں
    0.35
    ೩
    0.35
     ໜອງ
    0.35
    ೭
    0.35
    ecommerce
    0.34
    POSITIVE LOGITS
    Ber
    0.40
    Hol
    0.39
    |
    0.39
    New
    0.36
    Hel
    0.36
    نم
    0.35
    ?
    0.35
    Touch
    0.35
    Narr
    0.35
    Har
    0.34
    Act Density 0.000%

    No Known Activations