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

    Neuronpedia

    INDEX
    Explanations

    filling or unfilled states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Primary
    0.42
     primary
    0.41
    Turning
    0.40
     turnover
    0.39
    Primary
    0.38
     Hope
    0.38
     Coh
    0.38
     Turning
    0.38
     Iconic
    0.38
     Levi
    0.37
    POSITIVE LOGITS
     запол
    0.44
     wypeł
    0.43
     unfilled
    0.40
     filling
    0.39
     adquis
    0.38
    填充
    0.38
     rempl
    0.36
     remplir
    0.36
    otransferase
    0.36
     proud
    0.36
    Act Density 0.000%

    No Known Activations