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

    Neuronpedia

    INDEX
    Explanations

    your local

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kind
    0.41
     sake
    0.36
     request
    0.33
     outburst
    0.32
     bid
    0.32
    डून
    0.30
     claim
    0.30
     name
    0.29
     mandate
    0.29
     cliche
    0.29
    POSITIVE LOGITS
     देशों
    0.31
     স্থানীয়
    0.31
    地域の
    0.31
     Abu
    0.29
     lokalen
    0.29
     proveedores
    0.28
     httpServer
    0.28
     γλώ
    0.28
     vaisse
    0.28
     Carrying
    0.27
    Act Density 0.017%

    No Known Activations