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

    Neuronpedia

    INDEX
    Explanations

    references to people, organizations, or roles in various contexts

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

    Following a pronoun/noun with a preposition

    np_acts-logits-general · gemini-2.0-flash

    putting something in a position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    @[+][
    -0.67
    ddots
    -0.65
    :+:
    -0.59
     rospy
    -0.59
     onCreateView
    -0.58
    Lähteet
    -0.58
    SpringBootTest
    -0.57
    apunov
    -0.53
     Lesser
    -0.53
    TagMode
    -0.52
    POSITIVE LOGITS
     into
    0.78
     squarely
    0.67
     ahead
    0.60
     firmly
    0.57
     on
    0.52
     behind
    0.51
     onto
    0.50
     front
    0.49
     vào
    0.48
    +#+#
    0.47
    Act Density 0.135%

    No Known Activations