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

    Neuronpedia

    INDEX
    Explanations

    specific references to historical figures or events

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

    Code, database, or technical terms

    np_acts-logits-general · gemini-2.0-flash

    roles and treatment contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (“
    -0.93
     (“
    -0.91
     ("
    -0.83
     “
    -0.81
     “(
    -0.81
    -“
    -0.79
     "
    -0.75
    :“
    -0.75
    ，“
    -0.74
    =“
    -0.71
    POSITIVE LOGITS
     s
    0.77
     The
    0.76
     This
    0.70
     uite
    0.70
     quot
    0.70
     What
    0.64
    The
    0.63
     noastre
    0.61
     There
    0.59
    Chapter
    0.59
    Act Density 0.094%

    No Known Activations