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

    Neuronpedia

    INDEX
    Explanations

    go + directional adverbs/prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.40
    Bud
    0.37
    Glo
    0.37
     Spot
    0.37
     Scroll
    0.35
     Civ
    0.34
    Conven
    0.34
     Convention
    0.34
     größten
    0.34
    '
    0.34
    POSITIVE LOGITS
     overboard
    0.86
     astray
    0.68
     fishing
    0.68
     bananas
    0.64
     snorkeling
    0.61
     into
    0.61
     bankrupt
    0.61
     unnoticed
    0.57
     shopping
    0.56
     skiing
    0.55
    Act Density 0.031%

    No Known Activations