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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating new developments or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    latest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gră
    -0.44
    تقاوى
    -0.35
     szkol
    -0.33
     dasarnya
    -0.33
     čern
    -0.33
    huizen
    -0.33
     conmigo
    -0.32
     contém
    -0.31
     jardín
    -0.30
     kerst
    -0.30
    POSITIVE LOGITS
     latest
    0.96
    latest
    0.95
    Latest
    0.93
     LATEST
    0.91
    LATEST
    0.90
     Latest
    0.89
    Newest
    0.82
     recent
    0.78
     newest
    0.78
    recent
    0.76
    Act Density 0.094%

    No Known Activations