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

    Neuronpedia

    INDEX
    Explanations

    features related to product specifications and performance

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

    describing positive qualities

    np_acts-logits-general · gemini-2.0-flash

    positive descriptions of features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.69
     CreateTagHelper
    -0.61
     faktisk
    -0.57
     nemlig
    -0.56
    findpost
    -0.53
     '{@
    -0.52
     }}">
    -0.52
    agisse
    -0.51
     يتيمه
    -0.51
     faktiskt
    -0.49
    POSITIVE LOGITS
    ITECH
    0.66
    ArgsConstructor
    0.60
    Datuak
    0.57
     ARI
    0.56
    ngdoc
    0.55
    UnifiedTopology
    0.53
    prefixer
    0.53
    VersionUID
    0.52
     TTT
    0.52
     TPR
    0.50
    Act Density 0.040%

    No Known Activations