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

    Neuronpedia

    INDEX
    Explanations

    URLs and service links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मेस्टर
    0.35
    फेसर
    0.34
     reinvigor
    0.34
     फीसदी
    0.33
    %">
    0.33
    ishments
    0.33
     отдельных
    0.33
    stå
    0.33
     щодо
    0.33
    ເພື່ອ
    0.33
    POSITIVE LOGITS
     de
    0.39
     id
    0.35
     d
    0.34
     du
    0.33
     dari
    0.32
     e
    0.32
     E
    0.32
     o
    0.32
     at
    0.31
     from
    0.31
    Act Density 0.000%

    No Known Activations