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

    Neuronpedia

    INDEX
    Explanations

    references to movement and transitions into spaces or rooms

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

    entering spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prieten
    -0.49
     betrekking
    -0.44
     Standort
    -0.42
     lazy
    -0.41
    seamnă
    -0.41
     originaux
    -0.40
    KeyPair
    -0.39
    research
    -0.39
    tableFuture
    -0.39
    obrázek
    -0.39
    POSITIVE LOGITS
     inside
    0.73
    Inside
    0.70
    Entering
    0.68
    StoryboardSegue
    0.68
     INSIDE
    0.67
     Inside
    0.67
     Entering
    0.67
    inside
    0.66
     into
    0.63
     entering
    0.61
    Act Density 0.042%

    No Known Activations