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

    Neuronpedia

    INDEX
    Explanations

    phrases and actions related to invention and announcements

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

    actions by pairs or groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.58
    }{*}{}
    -0.54
     NgModule
    -0.52
    IContainer
    -0.52
     Züge
    -0.50
     desnuda
    -0.44
    richTextPanel
    -0.43
     térm
    -0.43
     ſes
    -0.42
     narrower
    -0.41
    POSITIVE LOGITS
     themselves
    0.58
     duo
    0.56
    themselves
    0.55
    二人
    0.53
     brothers
    0.49
    brothers
    0.46
     cherchés
    0.45
    Their
    0.44
     siblings
    0.44
     berdua
    0.43
    Act Density 0.408%

    No Known Activations