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

    Neuronpedia

    INDEX
    Explanations

    ## Introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etc
    0.31
     यामुळे
    0.31
    çando
    0.29
    性和
    0.29
    等を
    0.28
    会将
    0.28
    这将
    0.28
    னையும்
    0.28
    파일명
    0.27
    cean
    0.27
    POSITIVE LOGITS
     είναι
    0.37
    ！？
    0.32
     EXIST
    0.29
     MPa
    0.29
     имеет
    0.28
    ？！
    0.28
     merino
    0.28
     –
    0.28
     არის
    0.28
     transmutation
    0.28
    Act Density 0.318%

    No Known Activations