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

    Neuronpedia

    INDEX
    Explanations

    CM/CC abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unlawfully
    0.80
    ät
    0.80
    πό
    0.79
    igen
    0.79
     выстав
    0.78
     આમ
    0.78
    энд
    0.76
    ект
    0.76
     सहज
    0.76
    л
    0.75
    POSITIVE LOGITS
     CM
    0.94
    theorem
    0.93
    &$\
    0.90
    ICAGO
    0.88
    ;">
    0.88
    ACKS
    0.87
    ²/
    0.87
    ന്നു
    0.87
     dust
    0.86
     milled
    0.85
    Act Density 0.066%

    No Known Activations