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

    Neuronpedia

    INDEX
    Explanations

    different or comparing metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आसार
    0.45
     रीजनिंग
    0.45
     Applications
    0.45
     권
    0.44
    讠
    0.44
     нажа
    0.43
    Applications
    0.42
    一
    0.42
    镭
    0.41
     Asthma
    0.41
    POSITIVE LOGITS
     compared
    0.49
     usuario
    0.47
     suyo
    0.43
     comparação
    0.43
     designee
    0.43
     irmã
    0.42
     município
    0.42
     kriter
    0.42
     unique
    0.42
     distillery
    0.41
    Act Density 0.006%

    No Known Activations