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

    Neuronpedia

    INDEX
    Explanations

    references to assistance and support in professional contexts

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

    Following verbs like help, tell, hear

    np_acts-logits-general · gemini-2.0-flash

    addressing you or your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.72
     pihaknya
    -0.54
    ')->
    -0.53
     mich
    -0.52
    ที
    -0.52
    Хочу
    -0.49
    queryInterface
    -0.49
    myself
    -0.48
    :],
    -0.48
    ")->
    -0.48
    POSITIVE LOGITS
     you
    2.56
     your
    2.21
    your
    1.89
    you
    1.83
     yours
    1.75
     YOU
    1.64
    Your
    1.63
     YOUR
    1.63
     Your
    1.55
     вас
    1.52
    Act Density 0.714%

    No Known Activations