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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and statements

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

    that is, followed by clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.63
     Administrativna
    -0.61
     kaarangay
    -0.59
    хьтан
    -0.58
    MessageOf
    -0.55
     дописавши
    -0.54
     vPvB
    -0.50
    olol
    -0.48
     kasarigan
    -0.48
    Externé
    -0.48
    POSITIVE LOGITS
     []).
    0.40
     terciopelo
    0.37
     Namely
    0.35
    PARATUS
    0.34
    ruptedException
    0.33
     Leopoldo
    0.33
     nämlich
    0.33
    Vaata
    0.32
     때문
    0.32
     yaitu
    0.32
    Act Density 0.019%

    No Known Activations