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

    Neuronpedia

    INDEX
    Explanations

    remote job teams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immune
    0.43
    ectin
    0.42
     M
    0.42
     préalable
    0.41
    h
    0.41
    M
    0.41
     activation
    0.41
     boasts
    0.41
     serde
    0.40
     d
    0.40
    POSITIVE LOGITS
     именно
    0.45
     больше
    0.42
    ánsito
    0.42
    っぽ
    0.42
     много
    0.41
    力を
    0.41
     новой
    0.41
     nuevas
    0.41
     Много
    0.40
     новые
    0.39
    Act Density 0.001%

    No Known Activations