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

    Neuronpedia

    INDEX
    Explanations

    packing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rinth
    0.64
    abilistic
    0.63
     يتيمه
    0.63
     ಫಲ
    0.62
    งาน
    0.62
    ógł
    0.60
    żyt
    0.59
     پرورش
    0.59
    顧客
    0.58
    娼
    0.58
    POSITIVE LOGITS
     sunscreen
    1.55
     snacks
    1.39
     toiletries
    1.32
     waterproof
    1.25
     portable
    1.23
     Snacks
    1.21
     essentials
    1.16
     sunglasses
    1.13
     Portable
    1.12
     hydration
    1.11
    Act Density 0.099%

    No Known Activations