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

    Neuronpedia

    INDEX
    Explanations

    meanings and expressions of agreement and admiration

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

    states a tendency or inclination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.53
     gynhyrchwyd
    -0.52
    الحياه
    -0.52
    +#+#
    -0.52
     transfieras
    -0.51
     Савезне
    -0.50
    GEBURTSDATUM
    -0.50
     Chwiliwch
    -0.50
    Controllo
    -0.49
    __":
    -0.49
    POSITIVE LOGITS
     tends
    0.63
     tend
    0.62
     tended
    0.54
     costuma
    0.49
     tiende
    0.48
     tienden
    0.48
     particularly
    0.47
     bý
    0.46
     rather
    0.44
     suelen
    0.43
    Act Density 0.024%

    No Known Activations