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

    Neuronpedia

    INDEX
    Explanations

    books and literary works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decreases
    0.31
     additives
    0.31
     nutrientes
    0.31
     stressors
    0.31
     används
    0.30
     diminuer
    0.30
     emitters
    0.30
     saludables
    0.30
     consumers
    0.30
     actuators
    0.30
    POSITIVE LOGITS
     trilogy
    0.55
     anthology
    0.46
     prequel
    0.45
     Trilogy
    0.42
     роман
    0.40
     című
    0.40
    judul
    0.39
     sequel
    0.38
     romanzo
    0.38
     masterpiece
    0.38
    Act Density 0.580%

    No Known Activations