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

    Neuronpedia

    INDEX
    Explanations

    common phrases and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scratching
    0.42
     چکی
    0.41
    芾
    0.41
     grinning
    0.40
    Wool
    0.39
    Smiling
    0.38
    smiling
    0.38
    ρική
    0.38
     पढ़ा
    0.37
     মেশিন
    0.37
    POSITIVE LOGITS
    insert
    0.39
    num
    0.38
     उठे
    0.38
    એસ
    0.37
    ⓓ
    0.37
    acter
    0.36
     >,
    0.35
     Germans
    0.35
     Counter
    0.35
     cont
    0.34
    Act Density 0.013%

    No Known Activations