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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts that emphasize uniqueness or exclusivity

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

    unique or only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    buttonShape
    -0.40
     ambassade
    -0.40
    leştir
    -0.36
     takiego
    -0.36
     embaj
    -0.36
     diesen
    -0.35
    BLANK
    -0.35
     déplacements
    -0.35
     schlägt
    -0.35
    Становништво
    -0.35
    POSITIVE LOGITS
    satunya
    0.96
    httphttps
    0.85
    唯一
    0.83
     sole
    0.81
    唯一的
    0.76
    Sole
    0.73
     един
    0.69
     einzig
    0.69
     jedin
    0.69
     única
    0.68
    Act Density 0.066%

    No Known Activations