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

    Neuronpedia

    INDEX
    Explanations

    online resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caregiver
    0.37
     cray
    0.36
     mouseDown
    0.36
     closet
    0.35
    ()-
    0.35
     preservar
    0.34
     investigaciones
    0.34
     convertible
    0.34
     transferable
    0.33
    Leer
    0.33
    POSITIVE LOGITS
    ផលិត
    0.45
    GUILayout
    0.44
    志森
    0.44
    毎
    0.43
    𐰼
    0.43
     Tư
    0.43
     Giri
    0.43
    굉
    0.43
    ᱖
    0.42
    zarchiwizowane
    0.41
    Act Density 0.002%

    No Known Activations