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

    Neuronpedia

    INDEX
    Explanations

    action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nf
    -0.30
    inet
    -0.28
    æķ£
    -0.28
     TMPro
    -0.25
    renal
    -0.25
    jem
    -0.25
    {:
    -0.24
     ÄijáºŃu
    -0.24
    çľĭä½ł
    -0.24
    айн
    -0.24
    POSITIVE LOGITS
     cou
    0.27
    æĮij
    0.26
     cord
    0.25
     Bib
    0.25
    æľ¬
    0.25
    gü
    0.24
    stead
    0.24
    è³ŀ
    0.24
    ,w
    0.23
    ::_
    0.23
    Act Density 0.067%

    No Known Activations