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

    Neuronpedia

    INDEX
    Explanations

    online event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    】【
    0.46
    Radiux
    0.45
     eyeballs
    0.44
    `],
    0.43
    椃
    0.42
     dí
    0.42
     nhựa
    0.42
     सीड्स
    0.41
     प्लास्टिक
    0.41
    rowad
    0.41
    POSITIVE LOGITS
     digamos
    0.39
     poteva
    0.36
    cznej
    0.36
    уре
    0.36
    Ket
    0.34
    Gallery
    0.33
     dug
    0.33
     lags
    0.33
     vivos
    0.33
    캡
    0.33
    Act Density 0.002%

    No Known Activations