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

    Neuronpedia

    INDEX
    Explanations

    elements related to software dependencies and configurations

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

    configuration parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ainfi
    -0.52
    adaptiveStyles
    -0.51
     mauva
    -0.46
    vistar
    -0.45
     dévelo
    -0.45
     avoient
    -0.45
     étoit
    -0.44
     pouvoit
    -0.43
     sourire
    -0.43
     aussitôt
    -0.43
    POSITIVE LOGITS
    MessageOf
    0.62
    enumi
    0.59
    httphttps
    0.57
     Савезне
    0.55
    tonode
    0.53
     <>",
    0.53
    +#+#
    0.52
     dAtA
    0.49
    setof
    0.46
    principalColumn
    0.46
    Act Density 0.042%

    No Known Activations