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

    Neuronpedia

    INDEX
    Explanations

    specific pronouns and particles in various contexts

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

    words ending in id, ites, ids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.65
     SwitchCompat
    -0.59
    HomeAsUpEnabled
    -0.59
    (!__
    -0.56
    AsUp
    -0.56
     arşivlendi
    -0.55
    twimg
    -0.51
    Snapchat
    -0.49
    pona
    -0.49
    ſelf
    -0.48
    POSITIVE LOGITS
    rik
    0.87
    ri
    0.75
     ri
    0.75
    rica
    0.73
    ria
    0.73
    ric
    0.72
    rico
    0.71
    rij
    0.71
    arik
    0.70
    rid
    0.69
    Act Density 0.055%

    No Known Activations