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

    Neuronpedia

    INDEX
    Explanations

    preparation steps or procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    гистра
    0.44
    濆
    0.43
    이나
    0.41
     সাধারণত
    0.40
     ప్రాంత
    0.40
     ouvrir
    0.40
    岃
    0.39
     verbre
    0.39
    ⎆
    0.38
     কারণে
    0.38
    POSITIVE LOGITS
    ТА
    0.45
     AMAZING
    0.44
    >?
    0.43
    Newly
    0.42
     BOOK
    0.41
     think
    0.40
    lL
    0.39
    EEN
    0.39
    tram
    0.39
     Malaysian
    0.38
    Act Density 0.000%

    No Known Activations