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

    Neuronpedia

    INDEX
    Explanations

    anatomy and skin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Then
    0.42
     następnie
    0.40
     然后
    0.40
     тоді
    0.38
     then
    0.38
     Instant
    0.38
     rồi
    0.37
     instantaneous
    0.37
    导师
    0.37
    ေး
    0.36
    POSITIVE LOGITS
    सबसे
    0.47
     nowadays
    0.47
    Pokud
    0.45
    awsze
    0.45
    Nowadays
    0.45
     показывать
    0.44
     कार्यरत
    0.43
    如果你
    0.43
    আপনার
    0.43
    ļa
    0.43
    Act Density 0.040%

    No Known Activations