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

    Neuronpedia

    INDEX
    Explanations

    after or succeeding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পাকিস্তানে
    0.39
     nowhere
    0.38
    -)
    0.38
     primeros
    0.37
     elsewhere
    0.37
    ritical
    0.36
     )-
    0.36
     groundwork
    0.35
     Polsce
    0.35
     sobretudo
    0.34
    POSITIVE LOGITS
     after
    0.43
     setelah
    0.42
     μετά
    0.41
    after
    0.40
     efter
    0.40
     nakon
    0.39
     после
    0.38
     بعد
    0.38
     संग
    0.38
     após
    0.37
    Act Density 0.015%

    No Known Activations