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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "some" and variations of it

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

    Followed by a noun or adjective

    np_acts-logits-general · gemini-2.0-flash

    some followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    -0.69
    <b>
    -0.51
     trocar
    -0.50
     cockroach
    -0.49
    lafen
    -0.48
     Batam
    -0.48
     oorsp
    -0.48
     autorisés
    -0.45
    </b>
    -0.44
     aceasta
    -0.43
    POSITIVE LOGITS
     виправивши
    1.05
    abetes
    0.96
    ContentAsync
    0.89
    }}">
    0.88
    SOME
    0.88
    ciutto
    0.87
     nice
    0.84
    ]=="
    0.83
     sort
    0.82
    "):
    0.82
    Act Density 0.125%

    No Known Activations