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

    Neuronpedia

    INDEX
    Explanations

    steps or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     set
    0.55
    ↵
    0.51
     networking
    0.50
     detective
    0.50
     hard
    0.50
     dedication
    0.49
    c
    0.48
     digital
    0.48
     Westfield
    0.48
     commodity
    0.48
    POSITIVE LOGITS
     }{}_{\
    0.54
    的最大
    0.50
    0.50
    acées
    0.48
    ಪ್ಪ
    0.47
    onnés
    0.47
     захворю
    0.47
     стандарта
    0.47
    érieur
    0.46
    벌
    0.46
    Act Density 0.003%

    No Known Activations