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

    Neuronpedia

    INDEX
    Explanations

    list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ซิตี
    0.44
    ಟ
    0.41
    <0xE4>
    0.40
    mataspid
    0.40
    剧
    0.39
    ***
    0.39
     لوبو
    0.38
    ὁ
    0.38
    എ
    0.38
    应当
    0.38
    POSITIVE LOGITS
     êtres
    0.45
     autoridad
    0.42
    .
    0.41
     sparen
    0.40
     llegar
    0.39
     іх
    0.39
     otten
    0.39
     leurs
    0.38
     שהוא
    0.37
     തോന്ന
    0.37
    Act Density 4.298%

    No Known Activations