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

    Neuronpedia

    INDEX
    Explanations

    end of code lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Doch
    0.39
     লিখিয়াছেন
    0.39
    Normdaten
    0.38
    കു
    0.36
    タブ
    0.36
    மார்
    0.35
     জের
    0.35
     pestaña
    0.35
     पंकज
    0.35
    नॉ
    0.34
    POSITIVE LOGITS
    ;
    0.51
    ؛
    0.45
    ；
    0.44
     :)
    0.43
     ;)
    0.39
    $;
    0.38
     ؛
    0.38
     itself
    0.37
     anyway
    0.37
     rồi
    0.36
    Act Density 0.029%

    No Known Activations