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

    Neuronpedia

    INDEX
    Explanations

    business plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mamm
    0.80
    Tele
    0.78
    வை
    0.76
    Reception
    0.74
    Reservation
    0.74
    RGB
    0.73
     vacances
    0.72
    🔍
    0.72
    Monday
    0.72
    comput
    0.72
    POSITIVE LOGITS
     Note
    0.71
     ści
    0.70
     facing
    0.68
     ดังนั้น
    0.65
     simultaneously
    0.65
     Stylish
    0.65
     Hence
    0.64
     Feel
    0.64
     Facing
    0.63
     nécessaire
    0.63
    Act Density 0.131%

    No Known Activations