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

    Neuronpedia

    INDEX
    Explanations

    various, different, many

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pe
    0.38
    aine
    0.38
      
    0.36
    the
    0.36
    either
    0.34
    wa
    0.34
    timestep
    0.34
    fresh
    0.33
     either
    0.33
    atea
    0.33
    POSITIVE LOGITS
     różnych
    0.49
     المختلفة
    0.47
     různých
    0.46
     várias
    0.44
     verschiedenen
    0.44
     amelyek
    0.43
     различ
    0.43
     різних
    0.43
     różne
    0.43
    いろいろ
    0.42
    Act Density 0.391%

    No Known Activations