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

    Neuronpedia

    INDEX
    Explanations

    code and French text

    oai_token-act-pair · gemini-2.0-flash

    m

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voici
    -0.60
     odeur
    -0.54
    Нау
    -0.54
     sensibilité
    -0.53
     blessure
    -0.52
     Guinée
    -0.51
     blessures
    -0.50
    retung
    -0.49
    énu
    -0.49
    Circ
    -0.48
    POSITIVE LOGITS
     "..\..\
    0.71
     cream
    0.68
     cremation
    0.67
    cream
    0.63
     referenties
    0.61
    crème
    0.59
     creams
    0.59
     FontWeight
    0.58
    fromnode
    0.57
    žd
    0.56
    Act Density 0.365%

    No Known Activations