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

    Neuronpedia

    INDEX
    Explanations

    technical or scientific terms related to methodologies and their applications

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

    followed by a form of "to be"

    np_acts-logits-general · gemini-2.0-flash

    modal verbs + past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.56
    strdup
    -0.55
    googleapis
    -0.55
     EconPapers
    -0.53
    <!--[
    -0.52
     transfieras
    -0.51
    ніципалі
    -0.51
    Didn
    -0.51
     there
    -0.51
    endforeach
    -0.50
    POSITIVE LOGITS
     was
    1.08
     veniva
    0.95
     został
    0.94
     été
    0.94
     být
    0.93
     została
    0.93
     être
    0.92
     được
    0.90
     zostało
    0.85
     zostanie
    0.85
    Act Density 1.649%

    No Known Activations