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

    Neuronpedia

    INDEX
    Explanations

    defining requirements and equipment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    딜
    0.45
    ]._
    0.44
    Pack
    0.43
    Dere
    0.42
     Dillon
    0.41
    Hart
    0.40
     डिल
    0.40
    Dil
    0.40
    ɭ
    0.40
    );">
    0.39
    POSITIVE LOGITS
     meal
    0.40
    WriteString
    0.38
     风
    0.37
     peroxidation
    0.36
     செய்வத
    0.36
     vyh
    0.36
     Современ
    0.36
    Ꞌ
    0.36
     Colonel
    0.35
     vzh
    0.35
    Act Density 0.000%

    No Known Activations