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

    Neuronpedia

    INDEX
    Explanations

    names of directors and production companies related to films

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

    Follows periods, often indicating end of sentence

    np_acts-logits-general · gemini-2.0-flash

    end of sentence/list item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.68
    exitRule
    -0.68
    ProcessEvent
    -0.56
     lignes
    -0.55
     vacanze
    -0.54
    تقاوى
    -0.53
     Wikispecies
    -0.53
    Попис
    -0.53
    fjspx
    -0.52
    /**
    -0.51
    POSITIVE LOGITS
     ($
    0.63
    IBarButtonItem
    0.56
    ReusableCell
    0.55
    [$
    0.54
     Vainqueur
    0.53
     [$
    0.52
     marketed
    0.51
     garnet
    0.51
     Garnet
    0.49
     pique
    0.49
    Act Density 0.523%

    No Known Activations