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

    Neuronpedia

    INDEX
    Explanations

    posts introducing a topic or inviting engagement with the audience

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

    Followed by "the", "this", or "on" in forum context

    np_acts-logits-general · gemini-2.0-flash

    forum and threads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.74
    INSEE
    -0.52
    CAPTION
    -0.50
    ifikationer
    -0.47
     PropTypes
    -0.46
    chinen
    -0.46
    robe
    -0.46
    Expedia
    -0.45
    ModelSerializer
    -0.45
    arakhand
    -0.44
    POSITIVE LOGITS
     forum
    2.26
     forums
    2.13
     Forum
    1.92
     Forums
    1.85
    forum
    1.84
    Forum
    1.78
     FORUM
    1.73
    forums
    1.58
     thread
    1.58
     threads
    1.53
    Act Density 0.283%

    No Known Activations