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

    Neuronpedia

    INDEX
    Explanations

    also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     тільки
    0.64
     only
    0.63
     nicht
    0.59
     tylko
    0.59
     फक्त
    0.58
     ekki
    0.58
     только
    0.58
     neither
    0.57
     not
    0.57
     endast
    0.57
    POSITIVE LOGITS
     also
    1.02
     också
    0.95
     también
    0.95
     גם
    0.93
    also
    0.90
     myös
    0.89
     også
    0.89
     juga
    0.88
     также
    0.88
     aussi
    0.87
    Act Density 0.175%

    No Known Activations