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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing emotional interactions or responses

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

    Japanese conjunctions

    np_acts-logits-general · gemini-2.0-flash

    Japanese conjunctive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    -1.27
    ，
    -1.15
    、
    -1.14
    ,
    -0.98
     ،
    -0.76
    、“
    -0.73
     ,
    -0.71
    ，「
    -0.68
    、「
    -0.68
    、《
    -0.67
    POSITIVE LOGITS
    そして
    1.01
    しかも
    0.87
    しかし
    0.84
     그리고
    0.84
     myſelf
    0.81
    また
    0.81
    ちなみに
    0.79
    ただし
    0.78
    これは
    0.75
    もちろん
    0.72
    Act Density 0.115%

    No Known Activations