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

    Neuronpedia

    INDEX
    Explanations

    specific examples or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ServiceNow
    0.34
    🛴
    0.34
     Laravel
    0.33
     webhook
    0.32
    に追加
    0.32
     onboarding
    0.32
     Shopify
    0.31
     চলতি
    0.31
     freelancer
    0.30
     ჩატი
    0.30
    POSITIVE LOGITS
    某些
    0.36
     cosidd
    0.34
     certains
    0.33
     vissa
    0.33
     algunas
    0.33
     certaines
    0.33
     phenomena
    0.32
     famously
    0.32
    据说
    0.31
     нередко
    0.31
    Act Density 0.926%

    No Known Activations