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

    Neuronpedia

    INDEX
    Explanations

    active verbs related to physical actions and interactions

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

    followed by prepositions/adverbs indicating direction

    np_acts-logits-general · gemini-2.0-flash

    verbs ending actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.72
    typeorm
    -0.68
    WriteTagHelper
    -0.67
    Хьажоргаш
    -0.64
    Personendaten
    -0.62
    awtextra
    -0.61
    theless
    -0.60
    osoba
    -0.58
    [...,
    -0.57
    insee
    -0.57
    POSITIVE LOGITS
     up
    1.26
     out
    1.26
    up
    0.86
     down
    0.85
     forth
    0.84
     off
    0.80
    out
    0.77
     back
    0.72
     away
    0.70
    tup
    0.70
    Act Density 0.424%

    No Known Activations