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

    Neuronpedia

    INDEX
    Explanations

    references to migration and border crossing

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

    followed by prepositions/punctuation

    np_acts-logits-general · gemini-2.0-flash

    while and that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     therefore
    -0.67
     Therefore
    -0.65
    ofern
    -0.61
    Therefore
    -0.59
     purpoſe
    -0.59
     separately
    -0.58
    Specifically
    -0.57
     independently
    -0.57
     actuellement
    -0.55
     actualmente
    -0.55
    POSITIVE LOGITS
     initComponents
    0.85
    while
    0.85
     mientras
    0.81
     seolah
    0.80
     while
    0.79
     persino
    0.78
     sambil
    0.78
     enquanto
    0.76
     mentre
    0.74
     terwijl
    0.72
    Act Density 0.609%

    No Known Activations