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

    Neuronpedia

    INDEX
    Explanations

    negations and terms related to statistical significance

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

    not statistically significant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.41
    konomi
    -0.38
    Lähteet
    -0.36
     autorytatywna
    -0.35
     başına
    -0.35
    HasForeignKey
    -0.34
     StatefulWidget
    -0.34
    ApiModelProperty
    -0.33
    Économie
    -0.32
    fizierung
    -0.32
    POSITIVE LOGITS
    évaluateur
    0.63
     تضيفلها
    0.51
     Otherwise
    0.51
    Otherwise
    0.50
     onCreateView
    0.50
    otherwise
    0.49
     otherwise
    0.48
    Abit
    0.47
     OTHERWISE
    0.46
    ########.
    0.45
    Act Density 0.197%

    No Known Activations