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

    Neuronpedia

    INDEX
    Explanations

    this is a statement opener

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     denkt
    0.29
     bits
    0.29
     rows
    0.28
     defined
    0.28
     Dateien
    0.26
     schemes
    0.26
    専用
    0.25
    葙
    0.25
     Mention
    0.25
     stories
    0.25
    POSITIVE LOGITS
     particular
    0.41
     morning
    0.37
     week
    0.35
    ንን
    0.35
    particular
    0.34
     konuda
    0.32
    morning
    0.32
     juncture
    0.32
     weekend
    0.30
     entire
    0.30
    Act Density 0.164%

    No Known Activations