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

    Neuronpedia

    INDEX
    Explanations

    expressions related to emotional experiences and personal relationships

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    verb-preposition phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ✨:
    -0.78
     nahilalakip
    -0.77
     esternos
    -0.74
    qrstuvwxyz
    -0.72
    hdashline
    -0.69
    Билгалдахарш
    -0.69
    rrggbb
    -0.68
     gynhyrchwyd
    -0.67
    urlpatterns
    -0.66
    انيف
    -0.65
    POSITIVE LOGITS
    titleMargin
    0.65
     towards
    0.57
     with
    0.55
     into
    0.55
     inmedi
    0.52
    ed
    0.51
     assiste
    0.50
     bygger
    0.49
     to
    0.49
     את
    0.48
    Act Density 0.946%

    No Known Activations