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

    Neuronpedia

    INDEX
    Explanations

    PM

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Through
    0.77
    ~$
    0.76
    .~
    0.73
    Through
    0.73
     melalui
    0.72
    through
    0.70
     through
    0.70
    ,~
    0.68
    .$\
    0.67
     attraverso
    0.67
    POSITIVE LOGITS
     gặp
    0.75
     departure
    0.71
     간
    0.69
    ärk
    0.68
     departures
    0.68
    akers
    0.67
     현
    0.66
    リティ
    0.65
    িকাল
    0.64
    '):
    0.64
    Act Density 0.016%

    No Known Activations