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

    Neuronpedia

    INDEX
    Explanations

    javascript function()

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಸ್ಥಾನ
    0.39
    ronom
    0.38
    收到
    0.37
     conjugate
    0.37
     dank
    0.37
     Levit
    0.37
     Rast
    0.36
     reprinted
    0.35
     Rendez
    0.35
    urent
    0.35
    POSITIVE LOGITS
     arbeiten
    0.43
    ($
    0.42
     works
    0.42
    ();
    0.41
    $)
    0.41
     ();
    0.41
    Works
    0.41
     worked
    0.40
     çalış
    0.40
     enc
    0.39
    Act Density 0.000%

    No Known Activations