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

    Neuronpedia

    INDEX
    Explanations

    references to past experiences or statuses

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

    past states of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bereitung
    -0.40
    ContentAlignment
    -0.39
     literally
    -0.38
    reactstrap
    -0.35
    `{.
    -0.32
    LOYEES
    -0.31
    atser
    -0.30
     literal
    -0.29
    literally
    -0.29
    Literal
    -0.29
    POSITIVE LOGITS
     للمعارف
    0.73
    новништво
    0.66
     CreateTagHelper
    0.65
    GOTREF
    0.60
     rhestr
    0.53
    ésultats
    0.53
    niſſe
    0.53
     autorytatywna
    0.51
    ◩
    0.49
    ſelf
    0.49
    Act Density 0.105%

    No Known Activations