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

    Neuronpedia

    INDEX
    Explanations

    responses that indicate careful and nuanced reasoning, especially in complex discussions.

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

    my, your, her possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    With
    0.42
    Within
    0.42
     respective
    0.41
     विभिन्न
    0.41
     within
    0.40
    Ingrese
    0.40
     jeweiligen
    0.39
    Ab
    0.39
    indeki
    0.39
    Ú
    0.39
    POSITIVE LOGITS
     goal
    0.48
     wife
    0.43
     eyes
    0.43
     fingers
    0.42
     aim
    0.41
     ancestors
    0.40
     brother
    0.40
    नाथन
    0.39
     ήταν
    0.39
     parents
    0.38
    Act Density 0.163%

    No Known Activations