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

    Neuronpedia

    INDEX
    Explanations

    explicit mentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caloric
    0.51
     calorie
    0.50
     elec
    0.50
    널
    0.50
    calories
    0.49
    পুর
    0.48
    病毒
    0.47
     footsteps
    0.46
     தேவையான
    0.46
     uttering
    0.46
    POSITIVE LOGITS
    kunde
    0.40
    上
    0.40
    鎿
    0.40
     প্রেক্ষিতে
    0.40
     BAM
    0.39
    အတ
    0.39
     Tanj
    0.38
     Prospect
    0.38
     Guilherme
    0.38
    ায
    0.38
    Act Density 0.001%

    No Known Activations