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

    Neuronpedia

    INDEX
    Explanations

    phrases that express inquiry or questions about capability and understanding

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

    French personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    je me demande

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     côtes
    -0.47
     Hongrie
    -0.45
     Tourisme
    -0.43
     répondit
    -0.43
     orejas
    -0.43
     Danemark
    -0.42
     romantique
    -0.42
     Unterhaltung
    -0.41
     Romains
    -0.41
    oreille
    -0.41
    POSITIVE LOGITS
     be
    0.57
     imp
    0.56
     @"/
    0.54
     have
    0.52
     createSlice
    0.52
     rec
    0.51
     stringBy
    0.50
     hod
    0.50
     burlap
    0.50
     log
    0.49
    Act Density 0.099%

    No Known Activations