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

    Neuronpedia

    INDEX
    Explanations

    tire sizes and SMS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     attrakt
    0.47
     testify
    0.42
     sone
    0.41
     jun
    0.40
     cities
    0.40
     Juni
    0.40
     parliament
    0.40
     Millennium
    0.39
     привлека
    0.39
     anlat
    0.38
    POSITIVE LOGITS
    ড়িয়ে
    0.40
    oreau
    0.38
    Profile
    0.37
    slime
    0.36
    Compression
    0.36
    Ộ
    0.36
    ovať
    0.35
    suffix
    0.35
    約
    0.35
    /
    0.35
    Act Density 0.001%

    No Known Activations