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

    Neuronpedia

    INDEX
    Explanations

    instances of communication and instruction

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

    recommend, encourage, suggest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.52
     arşivlendi
    -0.44
    XmlAccessType
    -0.40
     gebe
    -0.37
    AnchorStyles
    -0.36
     Island
    -0.36
    BindView
    -0.35
     External
    -0.35
    脈
    -0.34
     Yaw
    -0.33
    POSITIVE LOGITS
    SourceChecksum
    0.60
    mybatisplus
    0.46
    Encourage
    0.45
     Encourage
    0.42
     encourag
    0.42
    ۗ
    0.42
     encourage
    0.41
     reassure
    0.40
    ttemberg
    0.40
    @[+][
    0.40
    Act Density 0.174%

    No Known Activations