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

    Neuronpedia

    INDEX
    Explanations

    voltage and frequency specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insistent
    0.55
    TorpedoStore
    0.52
    寺
    0.52
     aumentando
    0.51
    人
    0.51
    ם
    0.51
    脅
    0.50
     tumbled
    0.50
    σει
    0.49
    ρι
    0.49
    POSITIVE LOGITS
    ،
    0.67
    ፣
    0.51
     newline
    0.49
     algebras
    0.49
     Acids
    0.48
     एशियाई
    0.48
     måde
    0.48
     were
    0.48
    ophyte
    0.47
    "،
    0.47
    Act Density 0.002%

    No Known Activations