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

    Neuronpedia

    INDEX
    Explanations

    references to direction and movement

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

    Comes before an infinitive verb

    np_acts-logits-general · gemini-2.0-flash

    to followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.70
     <=",
    -0.70
     Italijanski
    -0.69
     saites
    -0.66
    ModelBuilder
    -0.66
     exported
    -0.62
    Rhestr
    -0.62
    protoimpl
    -0.62
     migrating
    -0.60
    Ārējās
    -0.59
    POSITIVE LOGITS
     discuss
    0.60
     greet
    0.57
     investigate
    0.55
     celebrate
    0.55
     help
    0.51
    ]=(
    0.51
     examine
    0.51
     congratulate
    0.51
     بلکه
    0.50
     helpen
    0.48
    Act Density 0.226%

    No Known Activations