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

    Neuronpedia

    INDEX
    Explanations

    example situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     none
    0.44
     ตาม
    0.44
     another
    0.43
     Unlike
    0.43
     Deze
    0.43
    ି
    0.43
     alcune
    0.41
     outros
    0.40
     alguns
    0.40
     своїх
    0.40
    POSITIVE LOGITS
     situation
    0.62
     mediocre
    0.58
     perfectly
    0.51
     مثلا
    0.50
     violinist
    0.49
    например
    0.47
    situation
    0.47
     molecule
    0.46
     मसलन
    0.46
     ситуации
    0.46
    Act Density 0.018%

    No Known Activations