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

    Neuronpedia

    INDEX
    Explanations

    technical terms and definitions related to mechanics and machinery

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

    Followed by "of," "in," or "that"

    np_acts-logits-general · gemini-2.0-flash

    systems, representations, definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sneered
    -0.59
    MessageTagHelper
    -0.57
    +#+#
    -0.57
     wept
    -0.55
    ('/:
    -0.53
     <<<<<<<<<<<<<<
    -0.53
    ArgsConstructor
    -0.53
     APPELLATE
    -0.53
     castig
    -0.53
     assuredly
    -0.52
    POSITIVE LOGITS
     prêtres
    0.66
     usually
    0.65
    的一种
    0.64
     quæ
    0.64
    usually
    0.62
     mergeFrom
    0.61
    ^(@)
    0.61
    Usually
    0.59
    stateProvider
    0.59
    Datuak
    0.59
    Act Density 0.907%

    No Known Activations