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

    Neuronpedia

    INDEX
    Explanations

    the concept of connections or continuities

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

    series of events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ApiModelProperty
    -0.51
    paddingTop
    -0.43
     nakalista
    -0.42
     ESPA
    -0.40
    korb
    -0.38
    schung
    -0.38
    isDisabled
    -0.37
     Pardo
    -0.37
     Schwä
    -0.37
    dito
    -0.37
    POSITIVE LOGITS
    連
    2.25
    连
    2.11
     连
    1.83
     連
    1.63
     Lian
    1.30
    就连
    1.03
    lian
    1.01
     연
    1.00
    聯
    0.96
    联
    0.93
    Act Density 0.004%

    No Known Activations