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

    Neuronpedia

    INDEX
    Explanations

    google drive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    includes
    0.42
    াপিত
    0.41
    㖪
    0.41
    坴
    0.40
     supposing
    0.39
     COUNTRY
    0.39
     calmodulin
    0.39
    UTRAL
    0.39
     ।*
    0.38
    綀
    0.38
    POSITIVE LOGITS
     ফুট
    0.40
    Princ
    0.40
    Support
    0.39
    Tro
    0.39
    CAD
    0.39
    Lav
    0.38
    ListComponent
    0.38
    Plus
    0.38
    토
    0.38
    Pre
    0.38
    Act Density 0.000%

    No Known Activations