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

    Neuronpedia

    INDEX
    Explanations

    words related to keeping things, such as remembering passwords or staying connected

    oai_token-act-pair · gemini-2.0-flash

    words related to managing tasks or updates

    np_token-act-pair-logits · gpt-4o-mini

    Stay connected or active

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hålla
    -0.54
     Engaging
    -0.53
     Inspiring
    -0.51
    arko
    -0.48
    threatening
    -0.48
    breaking
    -0.48
    AndEndTag
    -0.47
    全文
    -0.47
    graceful
    -0.47
    growing
    -0.46
    POSITIVE LOGITS
     turned
    0.81
     pulled
    0.75
     converted
    0.75
     extracted
    0.74
     transformed
    0.71
     solved
    0.71
     settled
    0.71
     boosted
    0.70
    complexContent
    0.70
     edited
    0.70
    Act Density 1.881%

    No Known Activations