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

    Neuronpedia

    INDEX
    Explanations

    redirection operator `>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نوع
    0.44
     uitgebre
    0.43
     praktik
    0.42
     نوع
    0.41
    濫
    0.39
     felicit
    0.39
     Grac
    0.38
     الأكثر
    0.38
    Cay
    0.38
     mensch
    0.38
    POSITIVE LOGITS
     जले
    0.49
     NONE
    0.46
    ırd
    0.46
     بەر
    0.46
     divider
    0.45
    मोरी
    0.45
     específico
    0.44
     Milano
    0.44
    晧
    0.44
    точной
    0.43
    Act Density 0.002%

    No Known Activations