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

    Neuronpedia

    INDEX
    Explanations

    requests for feedback or assistance

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

    Requests or suggestions

    np_acts-logits-general · gemini-2.0-flash

    requests to chat or ask questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     egentlig
    -0.54
    gleich
    -0.52
    __":
    -0.51
    __':
    -0.48
     egentligen
    -0.48
     zwar
    -0.46
     single
    -0.45
    łożyć
    -0.45
    OOTDTY
    -0.44
    ciaż
    -0.43
    POSITIVE LOGITS
    Hentet
    0.68
    CloseOperation
    0.66
     nakalista
    0.65
    EndInit
    0.65
     defaultstate
    0.62
     GreatSchools
    0.62
     تضيفلها
    0.61
    tvguidetime
    0.61
    homonymie
    0.59
     kasarigan
    0.57
    Act Density 0.073%

    No Known Activations